examples of an literature review

PSYC 210: Foundations of Psychology

• Tips for Searching for Articles

What is a literature review?

Conducting a literature review, organizing a literature review, writing a literature review, helpful book.

• Avoiding Plagiarism
• Google Scholar

A  literature review  is a compilation of the works published in a particular field of study or line of research, usually over a specific period of time, in the form of an in-depth, critical bibliographic essay or annotated list in which attention is drawn to the most significant works.

• Summarizes and analyzes previous research relevant to a topic
• Includes scholarly books and articles published in academic journals
• Can be an specific scholarly paper or a section in a research paper

The objective of a Literature Review is to find previous published scholarly works relevant to an specific topic

• Help gather ideas or information
• Keep up to date in current trends and findings
• Help develop new questions

A literature review is important because it:

• Explains the background of research on a topic
• Demonstrates why a topic is significant to a subject area
• Helps focus your own research questions or problems
• Discovers relationships between research studies/ideas
• Suggests unexplored ideas or populations
• Identifies major themes, concepts, and researchers on a topic
• Tests assumptions; may help counter preconceived ideas and remove unconscious bias
• Identifies critical gaps, points of disagreement, or potentially flawed methodology or theoretical approaches

Source: "What is a Literature Review?", Old Dominion University,  https://guides.lib.odu.edu/c.php?g=966167&p=6980532

1. Choose a topic. Define your research question. 

Your literature review should be guided by a central research question. It represents background and research developments related to a specific research question, interpreted, and analyzed by you in a synthesized way. 

• Make sure your research question is not too broad or too narrow.
• Write down terms that are related to your question for they will be useful for searches later. 

2. Decide on the scope of your review. 

How many studies do you need to look at? How comprehensive should it be? How many years should it cover? 

• This may depend on your assignment.
• Consider these things when planning your time for research. 

3. Select the databases you will use to conduct your searches. 

• By Research Guide 

4. Conduct your searches and find the literature. 

• Review the abstracts carefully - this will save you time!
• Many databases will have a search history tab for you to return to for later.
• Use bibliographies and references of research studies to locate others.
• Use citation management software such as Zotero to keep track of your research citations. 

5. Review the literature. 

Some questions to help you analyze the research: 

• What was the research question you are reviewing? What are the authors trying to discover? 
• Was the research funded by a source that could influence the findings? 
• What were the research methodologies? Analyze the literature review, samples and variables used, results, and conclusions. Does the research seem complete? Could it have been conducted more soundly? What further questions does it raise? 
• If there are conflicted studies, why do you think that is? 
• How are the authors viewed in the field? Are they experts or novices? Has the study been cited? 

Source: "Literature Review", University of West Florida,  https://libguides.uwf.edu/c.php?g=215113&p=5139469

A literature review is not a summary of the sources but a synthesis of the sources. It is made up of the topics the sources are discussing. Each section of the review is focused on a topic, and the relevant sources are discussed within the context of that topic. 

1. Select the most relevant material from the sources

• Could be material that answers the question directly
• Extract as a direct quote or paraphrase 

2. Arrange that material so you can focus on it apart from the source text itself

• You are now working with fewer words/passages
• Material is all in one place

3. Group similar points, themes, or topics together and label them 

• The labels describe the points, themes, or topics that are the backbone of your paper’s structure

4. Order those points, themes, or topics as you will discuss them in the paper, and turn the labels into actual assertions

• A sentence that makes a point that is directly related to your research question or thesis 

This is now the outline for your literature review. 

Source: "Organizing a Review of the Literature – The Basics", George Mason University Writing Center,  https://writingcenter.gmu.edu/writing-resources/research-based-writing/organizing-literature-reviews-the-basics

• Literature Review Matrix Here is a template on how people tend to organize their thoughts. The matrix template is a good way to write out the key parts of each article and take notes. Downloads as an XLSX file.

The most common way that literature reviews are organized is by theme or author. Find a general pattern of structure for the review. When organizing the review, consider the following: 

• the methodology 
• the quality of the findings or conclusions
• major strengths and weaknesses
• any other important information

Writing Tips: 

• Be selective - Select only the most important points in each source to highlight in the review. It should directly relate to the review's focus.
• Use quotes sparingly.
• Keep your own voice - Your voice (the writer's) should remain front and center. .   
• Aim for one key figure/table per section to illustrate complex content, summarize a large body of relevant data, or describe the order of a process
• Legend below image/figure and above table and always refer to them in text 

Source: "Composing your Literature Review", Florida A&M University,  https://library.famu.edu/c.php?g=577356&p=3982811

• << Previous: Tips for Searching for Articles
• Next: Citing Your Sources >>
• Last Updated: Aug 21, 2024 3:43 PM
• URL: https://infoguides.pepperdine.edu/PSYC210

Explore. Discover. Create.

Copyright ©  2022  Pepperdine University

Literature Reviews

• Getting started

What is a literature review?

Why conduct a literature review, stages of a literature review, lit reviews: an overview (video), check out these books.

• Types of reviews
• 1. Define your research question
• 2. Plan your search
• 3. Search the literature
• 4. Organize your results
• 5. Synthesize your findings
• 6. Write the review
• Artificial intelligence (AI) tools
• Thompson Writing Studio This link opens in a new window
• Need to write a systematic review? This link opens in a new window

Guide Owner

Contact a Librarian

Ask a Librarian

Definition: A literature review is a systematic examination and synthesis of existing scholarly research on a specific topic or subject.

Purpose: It serves to provide a comprehensive overview of the current state of knowledge within a particular field.

Analysis: Involves critically evaluating and summarizing key findings, methodologies, and debates found in academic literature.

Identifying Gaps: Aims to pinpoint areas where there is a lack of research or unresolved questions, highlighting opportunities for further investigation.

Contextualization: Enables researchers to understand how their work fits into the broader academic conversation and contributes to the existing body of knowledge.

tl;dr  A literature review critically examines and synthesizes existing scholarly research and publications on a specific topic to provide a comprehensive understanding of the current state of knowledge in the field.

What is a literature review NOT?

❌ An annotated bibliography

❌ Original research

❌ A summary

❌ Something to be conducted at the end of your research

❌ An opinion piece

❌ A chronological compilation of studies

The reason for conducting a literature review is to:

Literature Reviews: An Overview for Graduate Students

While this 9-minute video from NCSU is geared toward graduate students, it is useful for anyone conducting a literature review.

Writing the literature review: A practical guide

Available 3rd floor of Perkins

Writing literature reviews: A guide for students of the social and behavioral sciences

Available online!

So, you have to write a literature review: A guided workbook for engineers

Telling a research story: Writing a literature review

The literature review: Six steps to success

Systematic approaches to a successful literature review

Request from Duke Medical Center Library

Doing a systematic review: A student's guide

• Next: Types of reviews >>
• Last Updated: Aug 29, 2024 11:40 AM
• URL: https://guides.library.duke.edu/litreviews

Services for...

• Faculty & Instructors
• Graduate Students
• Undergraduate Students
• International Students
• Patrons with Disabilities

• Harmful Language Statement
• Re-use & Attribution / Privacy
• Support the Libraries

• Frequently Asked Questions (FAQs)
• Terms and Conditions
• British Council Global
• Accessibility

© 2024 British Council

• Mini English Lessons

How to Write a Review That Stands Out: A Guide for English Learners

Writing an online review is a powerful way to share your experiences and help others make informed decisions.

This guide will help you understand how to write clear and effective reviews that offer valuable insights and help potential customers make decisions.

Things to consider before writing a review

What are you trying to achieve.

Before you start writing, think about what you want to achieve with your review. Are you trying to share a positive or negative experience? Do you want to provide valuable insights to help others? Do you just want to express your feelings?

Your review can influence a business’s online reputation and guide other customers, so be clear about your goal to make sure your review is helpful and effective.

How to format your review

Formatting your review properly is important to make sure it’s clear and easy to read. Start with a brief introduction that summarises your experience. Then, provide specific details about what you liked or didn’t like.

Use paragraphs to separate different points and make sure to proofread your review for any spelling or grammar mistakes. A well-formatted review shows your attention to detail and makes a stronger impact.

Consider your audience

Think about who will be reading your review. Are you addressing the company to provide feedback, or are you writing for other customers to help them make informed decisions?

Shape your language and specific details to suit your audience. For example, if you’re writing a review for other customers to read, focus on how the product or service met your needs and why you would highly recommend it (or not).

If you’re addressing the company, be sure to provide constructive feedback that could lead to improvements.

Types of reviews and how to write them

How to write a book review.

When writing a book review, include specific details about the plot, characters, and writing style. Mention what you liked or disliked and why. Your insights can have a significant impact on other readers.

Book review example sentences:

• “The author’s descriptive writing made the scenes come alive.”
• “I didn’t enjoy the book because it was slow and uneventful.”
• “The plot was engaging and full of unexpected twists, keeping me on the edge of my seat throughout the entire story.”

How to write a movie review

A good movie review should talk about the story, acting, and direction. Share your positive or negative thoughts and provide details. This helps others decide if they want to watch the movie.

Movie review example sentences:

• “The actors delivered outstanding performances.”
• “The direction was sloppy and uninspired, lacking any clear vision or creativity, which made the movie difficult to follow and unenjoyable to watch.”
• “The story was captivating from start to finish.”

How to write a product review

In a product review, describe how the product or service worked for you. Mention any customer service experiences. Be honest and include both pros and cons to give a balanced view. Good reviews are clear and helpful.

Product review example sentences:

• “The product worked perfectly and exceeded my expectations.”
• “I had a terrible experience with customer service, they were very unhelpful.”
• “I would not recommend this product to anyone; it broke after being used once.”

How to write a restaurant review

For a restaurant review, talk about the food, service, and atmosphere. Would you highly recommend the food? How was the customer service from the wait staff? Your review can help guide others looking for a great dining experience.

Restaurant review example sentences:

• “The food was delicious and beautifully presented.”
• “The service was slow and unprofessional.”
• “The atmosphere was noisy and uncomfortable; I would not eat here again.”

How to write a travel review

When writing a travel review, include specific details about the location, accommodation, and activities. Mention what you enjoyed and what could be improved. This helps others plan their trips better.

Travel review example sentences:

• “There were plenty of fun activities to do, and all within walking distance.”
• “I highly recommend this beautiful destination to other travellers.”
• “The hotel was hard to find, with poor signage and confusing directions, and once we finally arrived, it was not worth the effort due to its outdated facilities.”

How to write a customer service review

A customer service review should focus on the quality of service you received. Did the staff respond to your needs? Were they helpful? Customer reviews that highlight good or bad service can influence a company’s online reputation.

Customer service review example sentences:

• “The staff responded quickly and resolved my issue.”
• “Everyone was friendly and went above and beyond to make sure we had a good time.”
• “I’m very disappointed with the service. The staff were unresponsive, and my issue was not resolved despite multiple attempts to get help.”

Leave us a review in the comments section below!

Now that you’ve learned some top tips on how to write a review, it’s time to practice your skills! Leave a comment below and tell us what you thought of this article.

If you enjoyed these tips and want to improve your English even more, explore our English Online courses – they come highly recommended, as you can see in the review below!

Explore English Online courses >

British Council Online Course – the best course I have ever had

I am happy with the course as it is informative and educative. It has helped me to improve my knowledge of the English language. English is my second language. I’ve become a much more confident speaker of the English language thanks to this course.

I have enjoyed having classes in group as well as doing pre-class tasks on my own. I am happy that our group has had different teachers as we can improve our listening skills while listening to a new teacher and stay more focused on the material of the lesson. British Council teachers are professionals who help us a lot with learning and understanding the topics better. British Council, thank you for your work. 🙏

This review was posted on Trustpilot on 27 Apr 2024. See the original review here.

Leave a comment Cancel reply

Your email address will not be published. Required fields are marked *

Related Posts

• Social English

What to Write in a Birthday Card: Crafting Memorable Messages for Your Loved Ones

Explore examples of different types of birthday messages to help you create the perfect wishes for friends, family, and acquaintances. Advertisement Advertisement The power […]

Exploring and Understanding British Humour: A Guide for English Learners

British humour is renowned worldwide for its wit, cleverness, and unique charm. With National Joke Day approaching on August 16th, there’s no better time […]

Understanding Different Types of Poetry: A Journey from Past to Present

Poetry is a special way of using language to express emotions, tell stories, and share ideas. It has changed a lot over the years, […]

Get Exclusive access to offers and promotions

Enter your email address below to join the english online mailing list..

Personal details will be held by the British Council and will only be used in relation to your request. Please read our terms of use for more information.

Verbs are direct, vigorous communicators. Use a chosen verb tense consistently throughout the same and adjacent paragraphs of a paper to ensure smooth expression.

Use the following verb tenses to report information in APA Style papers.

Verb tense is covered in the seventh edition APA Style manuals in the Publication Manual Section 4.12 and the Concise Guide Section 2.12

From the APA Style blog

Check your tone: Keeping it professional

When writing an APA Style paper, present ideas in a clear and straightforward manner. In this kind of scholarly writing, keep a professional tone.

The “no second-person” myth

Many writers believe the “no second-person” myth, which is that there is an APA Style guideline against using second-person pronouns such as “you” or “your.” On the contrary, you can use second-person pronouns in APA Style writing.

The “no first-person” myth

Whether expressing your own views or actions or the views or actions of yourself and fellow authors, use the pronouns “I” and “we.”

Navigating the not-so-hidden treasures of the APA Style website

This post links directly to APA Style topics of interest that users may not even know exist on the website.

Welcome, singular “they”

This blog post provides insight into how this change came about and provides a forum for questions and feedback.

Advertisement

The 100 Best Books of the 21st Century: A Printable List

By The New York Times Books Staff Aug. 26, 2024

• Share full article

Print this version to keep track of what you’ve read and what you’d like to read. See the full project, including commentary about the books, here.

A PDF version of this document with embedded text is available at the link below:

Download the original document (pdf)

The New York Times Book Review I've I want THE 100 BEST BOOKS OF THE 21ST CENTURY read to it read it 1 My Brilliant Friend, by Elena Ferrante 26 26 Atonement, by lan McEwan 2 The Warmth of Other Suns, by Isabel Wilkerson 27 Americanah, by Chimamanda Ngozi Adichie 3 Wolf Hall, by Hilary Mantel 28 Cloud Atlas, by David Mitchell 4 The Known World, by Edward P. Jones 29 The Last Samurai, by Helen DeWitt 5 The Corrections, by Jonathan Franzen 30 Sing, Unburied, Sing, by Jesmyn Ward 6 2666, by Roberto Bolaño 31 White Teeth, by Zadie Smith 7 The Underground Railroad, by Colson Whitehead 32 The Line of Beauty, by Alan Hollinghurst 8 Austerlitz, by W.G. Sebald 33 Salvage the Bones, by Jesmyn Ward 9 Never Let Me Go, by Kazuo Ishiguro 34 Citizen, by Claudia Rankine 10 Gilead, by Marilynne Robinson 35 Fun Home, by Alison Bechdel 11 The Brief Wondrous Life of Oscar Wao, by Junot Díaz 36 Between the World and Me, by Ta-Nehisi Coates 12 The Year of Magical Thinking, by Joan Didion 37 The Years, by Annie Ernaux 13 The Road, by Cormac McCarthy 38 The Savage Detectives, by Roberto Bolaño 14 Outline, by Rachel Cusk 39 A Visit From the Goon Squad, by Jennifer Egan 15 Pachinko, by Min Jin Lee 40 H Is for Hawk, by Helen Macdonald 16 The Amazing Adventures of Kavalier & Clay, by Michael Chabon 41 Small Things Like These, by Claire Keegan 17 The Sellout, by Paul Beatty 42 A Brief History of Seven Killings, by Marlon James 18 Lincoln in the Bardo, by George Saunders 43 Postwar, by Tony Judt 19 Say Nothing, by Patrick Radden Keefe 44 The Fifth Season, by N.K. Jemisin 20 Erasure, by Percival Everrett 45 The Argonauts, by Maggie Nelson 21 Evicted, by Matthew Desmond 46 The Goldfinch, by Donna Tartt 22 22 Behind the Beautiful Forevers, by Katherine Boo 47 A Mercy, by Toni Morrison 23 Hateship, Friendship, Courtship, Loveship, Marriage, by Alice Munro 48 Persepolis, by Marjane Satrapi 24 The Overstory, by Richard Powers 49 The Vegetarian, by Han Kang 25 25 Random Family, by Adrian Nicole LeBlanc 50 Trust, by Hernan Diaz I've I want read to it read it

The New York Times Book Review I've I want THE 100 BEST BOOKS OF THE 21ST CENTURY read to it read it 51 Life After Life, by Kate Atkinson 52 52 Train Dreams, by Denis Johnson 53 Runaway, by Alice Munro 76 77 An American Marriage, by Tayari Jones 78 Septology, by Jon Fosse Tomorrow, and Tomorrow, and Tomorrow, by Gabrielle Zevin 54 Tenth of December, by George Saunders 55 The Looming Tower, by Lawrence Wright 56 The Flamethrowers, by Rachel Kushner 57 Nickel and Dimed, by Barbara Ehrenreich ཤྲཱ རྒྱ སྐྱ A Manual for Cleaning Women, by Lucia Berlin The Story of the Lost Child, by Elena Ferrante Pulphead, by John Jeremiah Sullivan. Hurricane Season, by Fernanda Melchor 58 Stay True, by Hua Hsu 83 When We Cease to Understand the World, by Benjamín Labatut 59 Middlesex, by Jeffrey Eugenides 84 The Emperor of All Maladies, by Siddhartha Mukherjee 60 Heavy, by Kiese Laymon 85 Pastoralia, by George Saunders 61 Demon Copperhead, by Barbara Kingsolver 86 Frederick Douglass, by David W. Blight 62 10:04, by Ben Lerner 87 Detransition, Baby, by Torrey Peters 63 Veronica, by Mary Gaitskill 88 The Collected Stories of Lydia Davis 64 The Great Believers, by Rebecca Makkai 89 The Return, by Hisham Matar 65 The Plot Against America, by Philip Roth 90 The Sympathizer, by Viet Thanh Nguyen 66 We the Animals, by Justin Torres 91 The Human Stain, by Philip Roth 67 Far From the Tree, by Andrew Solomon 92 The Days of Abandonment, by Elena Ferrante 68 The Friend, by Sigrid Nunez 93 Station Eleven, by Emily St. John Mandel 69 59 The New Jim Crow, by Michelle Alexander 94 On Beauty, by Zadie Smith 10 70 All Aunt Hagar's Children, by Edward P. Jones 95 Bring Up the Bodies, by Hilary Mantel 71 The Copenhagen Trilogy, by Tove Ditlevsen 96 Wayward Lives, Beautiful Experiments, by Saidiya Hartman 72 22 Secondhand Time, by Svetlana Alexievich 97 Men We Reaped, by Jesmyn Ward 73 The Passage of Power, by Robert A. Caro 98 Bel Canto, by Ann Patchett 74 Olive Kitteridge, by Elizabeth Strout 99 How to Be Both, by Ali Smith 75 15 Exit West, by Mohsin Hamid 100 Tree of Smoke, by Denis Johnson I've I want read to it read it

Blog The Education Hub

https://educationhub.blog.gov.uk/2024/08/20/gcse-results-day-2024-number-grading-system/

GCSE results day 2024: Everything you need to know including the number grading system

Thousands of students across the country will soon be finding out their GCSE results and thinking about the next steps in their education.   

Here we explain everything you need to know about the big day, from when results day is, to the current 9-1 grading scale, to what your options are if your results aren’t what you’re expecting.  

When is GCSE results day 2024?  

GCSE results day will be taking place on Thursday the 22 August.     

The results will be made available to schools on Wednesday and available to pick up from your school by 8am on Thursday morning.  

Schools will issue their own instructions on how and when to collect your results.   

When did we change to a number grading scale?  

The shift to the numerical grading system was introduced in England in 2017 firstly in English language, English literature, and maths.  

By 2020 all subjects were shifted to number grades. This means anyone with GCSE results from 2017-2020 will have a combination of both letters and numbers.  

The numerical grading system was to signal more challenging GCSEs and to better differentiate between students’ abilities - particularly at higher grades between the A *-C grades. There only used to be 4 grades between A* and C, now with the numerical grading scale there are 6.  

What do the number grades mean?  

The grades are ranked from 1, the lowest, to 9, the highest.  

The grades don’t exactly translate, but the two grading scales meet at three points as illustrated below.  

The bottom of grade 7 is aligned with the bottom of grade A, while the bottom of grade 4 is aligned to the bottom of grade C.    

Meanwhile, the bottom of grade 1 is aligned to the bottom of grade G.  

What to do if your results weren’t what you were expecting?  

If your results weren’t what you were expecting, firstly don’t panic. You have options.  

First things first, speak to your school or college – they could be flexible on entry requirements if you’ve just missed your grades.   

They’ll also be able to give you the best tailored advice on whether re-sitting while studying for your next qualifications is a possibility.   

If you’re really unhappy with your results you can enter to resit all GCSE subjects in summer 2025. You can also take autumn exams in GCSE English language and maths.  

Speak to your sixth form or college to decide when it’s the best time for you to resit a GCSE exam.  

Look for other courses with different grade requirements     

Entry requirements vary depending on the college and course. Ask your school for advice, and call your college or another one in your area to see if there’s a space on a course you’re interested in.    

Consider an apprenticeship    

Apprenticeships combine a practical training job with study too. They’re open to you if you’re 16 or over, living in England, and not in full time education.  

As an apprentice you’ll be a paid employee, have the opportunity to work alongside experienced staff, gain job-specific skills, and get time set aside for training and study related to your role.   

You can find out more about how to apply here .  

Talk to a National Careers Service (NCS) adviser    

The National Career Service is a free resource that can help you with your career planning. Give them a call to discuss potential routes into higher education, further education, or the workplace.   

Whatever your results, if you want to find out more about all your education and training options, as well as get practical advice about your exam results, visit the  National Careers Service page  and Skills for Careers to explore your study and work choices.   

You may also be interested in:

• Results day 2024: What's next after picking up your A level, T level and VTQ results?
• When is results day 2024? GCSEs, A levels, T Levels and VTQs

Tags: GCSE grade equivalent , gcse number grades , GCSE results , gcse results day 2024 , gsce grades old and new , new gcse grades

Sharing and comments

Share this page, related content and links, about the education hub.

The Education Hub is a site for parents, pupils, education professionals and the media that captures all you need to know about the education system. You’ll find accessible, straightforward information on popular topics, Q&As, interviews, case studies, and more.

Please note that for media enquiries, journalists should call our central Newsdesk on 020 7783 8300. This media-only line operates from Monday to Friday, 8am to 7pm. Outside of these hours the number will divert to the duty media officer.

Members of the public should call our general enquiries line on 0370 000 2288.

Sign up and manage updates

Follow us on social media, search by date.

Comments and moderation policy

• Open access
• Published: 21 August 2024

Evaluating the effectiveness of large language models in abstract screening: a comparative analysis

• Michael Li 1 ,
• Jianping Sun 2 &
• Xianming Tan   ORCID: orcid.org/0000-0002-5478-2269 1 , 3  

Systematic Reviews volume  13 , Article number:  219 ( 2024 ) Cite this article

323 Accesses

Metrics details

This study aimed to evaluate the performance of large language models (LLMs) in the task of abstract screening in systematic review and meta-analysis studies, exploring their effectiveness, efficiency, and potential integration into existing human expert-based workflows.

We developed automation scripts in Python to interact with the APIs of several LLM tools, including ChatGPT v4.0, ChatGPT v3.5, Google PaLM 2, and Meta Llama 2, and latest tools including ChatGPT v4.0 turbo, ChatGPT v3.5 turbo, Google Gemini 1.0 pro, Meta Llama 3, and Claude 3. This study focused on three databases of abstracts and used them as benchmarks to evaluate the performance of these LLM tools in terms of sensitivity, specificity, and overall accuracy. The results of the LLM tools were compared to human-curated inclusion decisions, gold standard for systematic review and meta-analysis studies.

Different LLM tools had varying abilities in abstract screening. Chat GPT v4.0 demonstrated remarkable performance, with balanced sensitivity and specificity, and overall accuracy consistently reaching or exceeding 90%, indicating a high potential for LLMs in abstract screening tasks. The study found that LLMs could provide reliable results with minimal human effort and thus serve as a cost-effective and efficient alternative to traditional abstract screening methods.

While LLM tools are not yet ready to completely replace human experts in abstract screening, they show great promise in revolutionizing the process. They can serve as autonomous AI reviewers, contribute to collaborative workflows with human experts, and integrate with hybrid approaches to develop custom tools for increased efficiency. As technology continues to advance, LLMs are poised to play an increasingly important role in abstract screening, reshaping the workflow of systematic review and meta-analysis studies.

Peer Review reports

Introduction

A systematic review is a rigorous form of research that collates and synthesizes all existing evidence on a specific research question [ 1 ]. It stands as a cornerstone not just in medical research but across diverse academic disciplines. Unlike traditional literature reviews, systematic reviews follow a comprehensive and standardized process, such as the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guideline [ 2 ], designed to minimize bias and ensure reproducibility. Therefore, these reviews are recognized as one of the zenith levels of evidence in evidence-based research [ 3 ] and play a pivotal role in shaping clinical guidelines, healthcare policies, and informing medical decisions [ 4 ].

Commencing with a well-articulated research question, a typical systematic review launches an exhaustive search strategy that subsequently sweeps through databases, such as PubMed and Embase, supplemented by additional sources such as clinical trial registries and pertinent article reference lists, with aims to capture all relevant studies and mitigate bias. Predetermined inclusion and exclusion criteria guide the subsequent screening and selection of studies, encompassing facts like study design, patient demographics, and intervention types. Reviewers, working independently, appraise each study’s eligibility, reconciling disagreements through discussions or third-party reviews. Data extraction and synthesis follow, either through meta-analysis or narrative synthesis, depending on the heterogeneity of the selected studies.

The practice of conducting systematic reviews has gained substantial popularity with considerable demand within the academic community. A notable reference [ 5 ] to this trend found that approximately 75 trials and potentially 11 systematic reviews are disseminated daily, based on data from around 2010. Moreover, a query for “systematic review” in the Google Scholar database yields approximately 17,000 entries that have been published within the year 2023 alone, which translates into about 51 systematic reviews per day, as observed on November 26, 2023. This expanding volume of literature underscores the critical role that systematic reviews play in the consolidation of research findings across various fields of study.

Despite their pivotal role, executing systematic reviews remains a formidable task due to the abstract screening, a key phase that can be overwhelmingly time-consuming due to its volume. For example, in Polanin et al. [ 6 ], the authors reported that the research staff screened 29,846 abstracts independently (14,923 unique citations were double screened) over the course of 189 days. In addition, the variability in reporting standards, use of jargon, and varied study designs can further complicate the abstract screening process [ 7 ]. Nevertheless, the repetitive nature of the task, combined with cognitive fatigue, can lead to human errors [ 8 , 9 ]. Recent advancements in machine learning (ML) and deep learning propose possible solutions to these challenges. However, traditional ML models, while promising, require domain-specific training, a time-consuming process that often demands manual labeling of datasets [ 10 ].

Advancements in natural language processing (NLP) and artificial intelligence (AI) are opening doors to address challenges in systematic reviews. Large language models (LLMs) like ChatGPT [ 11 ], PaLM [ 12 ], Llama [ 13 ], and Claude [ 14 ] are capturing the research community’s attention. Their collective potential, especially their capability to operate without exhaustive domain-specific training, makes them prime candidates for revolutionizing the systematic review process.

While each of the aforementioned AI tools brings its unique capabilities to the table, the fundamental question remains: How do they stack up, both individually and collectively, in the realm of abstract screening, against the human expert-based process? In pursuit of answers, this research seeks to thoroughly investigate the potential of ChatGPT, Google PaLM, Llama, and Claude in automating the crucial abstract screening phase integral to systematic reviews. Our goal is to rigorously compare the performance of these advanced AI-driven methods with existing machine learning (ML)-based approaches. In doing so, we aim to develop AI strategies that masterfully balance efficiency and accuracy with minimal human intervention, ultimately transforming systematic review practice across disciplines.

The use of NLP for abstract screening is established [ 10 , 15 ]. However, the application of LLMs specifically for this task is a nascent field [ 16 , 17 ]. This emerging area offers significant potential to improve efficiency and accuracy. Our study aims to fill this gap by providing a comprehensive analysis of LLM capabilities in abstract screening, laying the groundwork for future research and application. This is particularly relevant considering the rapid evolution of this technology, highlighting its potential to streamline systematic reviews now and in the future.

The remainder of this paper is structured to provide a comprehensive exploration of our topic. We begin with an in-depth examination of existing methods for abstract screening, including both manual and NLP-based approaches, laying the groundwork for understanding the current state of the field. We then introduce the use of large language model (LLM) tools for abstract screening, detailing our experimental design to meticulously evaluate their performance in this context. Subsequent sections present our empirical findings and results, shedding light on the capabilities and limitations of the AI tools in question. Finally, we engage in a thoughtful discussion, reflecting on the implications of our findings and considering the future trajectory of abstract screening in systematic reviews.

Existing approaches to abstract screening in systematic reviews

In the vast realm of systematic reviews, the critical task of abstract screening serves as a foundational step in curating the highest quality of evidence [ 2 ]. However, this process often presents significant challenges due to the involvement of sifting through large volumes of literature to identify those that align with predefined criteria. Over time, various methodologies, ranging from manual evaluations to sophisticated AI-driven techniques, have been proposed to address the complexities of this task. In this section, we first describe the existing approaches on their operational mechanisms and associated advantages and disadvantages.

Manual approach

Historically, the process of abstract screening was firmly rooted in manual evaluations. In this conventional approach, individual reviewers would scrutinize each abstract against predefined criteria [ 1 ]. The meticulous nature of this method required that multiple experts independently evaluate the literature to ensure both reliability and reduced biases [ 8 ]. While the depth of human expertise brought about nuanced understanding, the manual nature of this method made it both time-consuming and, at times, prone to human error [ 6 , 9 ].

NLP-based approach

As technology evolved, the field witnessed the incorporation of natural language processing (NLP) to automate abstract screening [ 10 ]. In this framework, abstract text undergoes preprocessing and vectorization. Supervised machine learning models, notably the support vector machine (SVM) and the random forest (RF), are then trained on this vectorized data to classify literature based on specific criteria [ 15 ]. The strength of this approach lies in its potential for efficiency. However, its efficacy and accuracy hinges heavily on the availability of a well-curated, labeled training set.

Zero-shot classification

A more recent and innovative approach is zero-shot classification, which was notably highlighted by Xian et al. [ 18 ]. Eschewing the need for an extensive labeled training dataset, zero-shot classification offers the allure of categorizing abstracts without prior domain-specific training. By calculating a probability score for each abstract, researchers obtain a dynamic measure of its alignment with predefined categories. While it does not require training for the machine learning model, the tradeoff is a loss of sensitivity and potential omissions of pertinent studies [ 19 ]. In this study, for a given set of abstracts, we first obtain embeddings (using OpenAI’s text embedding API, the babbage model) for abstracts and for a pre-specified description of an ideal study to include. We indeed use the inclusion/exclusion criteria (see “Examples of abstract screening by using LLMs,” “Automated workflow for streamlining abstract screening via ChatGPT and other tools,” and “ Study design ” sections) as the description of an ideal study to include. We then compute the cosine similarity score between each abstract (its embedding) and the pre-specified description (its embedding). We claim the top 10% (in terms of similarity) of abstracts as positive (i.e., a study should be included).

Hybrid approach

To reconcile the strengths and limitations of these models, a hybrid methodology has emerged [ 18 ]. It cleverly marries the rapid categorization capabilities of zero-shot classification with the precision of traditional machine learning models such as SVM and RF. Here, zero-shot classification provides an initial curation of all abstracts in the training set. Then, based on zero-shot classification’s curation, the abstracts with classification score higher than a pre-specified threshold are selected to undergo manual review to rectify zero-shot classification. The rectified classification then serves as a foundation for training traditional models, which are then employed for screening the broader dataset (e.g., in the testing set). The hybrid approach balances the speed of zero-shot and the precision of traditional ML, and potentially offers enhanced accuracy at reduced human efforts. However, this approach involves the use of multiple methodologies and still relies on well-curated, labeled training data (in this case, a subset of the whole training set). In this study, for a given set of abstracts, we rectify the “positive” abstracts (i.e., the top 10% of abstracts) identified by zero-shot, and then fit a classification model for rectified labels to the text embeddings of the corresponding abstracts using SVM. This learned classification model is then used to predict the class of other abstracts. We added the R code for the zero-shot and hybrid approaches to the GitHub repository https://github.com/mikeli380/LLMAbstractScreening .

Active learning approach

Active learning [ 20 , 21 , 22 ] is an innovative approach to machine learning that optimizes the training process by allowing the model to selectively query a human annotator for labels on the most informative data points. This method is particularly advantageous in scenarios where labeled data is scarce or expensive to obtain. Active learning models can start with minimal datasets, often requiring only one relevant and one irrelevant abstract, making them particularly suitable for tasks such as abstract screening, where the acquisition of large labeled datasets can be prohibitive.

The main advantage of active learning is its efficiency. By focusing on the most informative samples, it reduces the amount of data that needs to be labeled while still effectively training the model. This can significantly reduce the time and resources required for the annotation process. However, the effectiveness of active learning depends heavily on the initial selection of samples and the criteria used to determine the informativeness of subsequent data points. If not well calibrated, the model may request labels for data that do not significantly improve its performance, resulting in an inefficient use of resources. In addition, the iterative nature of querying and updating the model based on new labels can introduce complexity into the training process, potentially requiring more sophisticated infrastructure and oversight than traditional supervised learning methods.

While this study did not test active learning approaches for abstract screening, readers interested in exploring this methodology further are referred to [ 23 ] for detailed information on the application of active learning in abstract screening contexts.

• Large language models

Amidst the evolving methodologies described in the “ Existing approaches to abstract screening in systematic reviews ” section, modern AI tools based on large language models (LLMs), such as ChatGPT, PaLM, Llama, and Claude, are emerging as potential game-changers. Grounded in advanced language processing capabilities, these tools can be tailored to evaluate abstracts against nuanced criteria and offer detailed assessments and classifications. Their prowess signals transformative potential for abstract screening. In this section, we first present two examples to illustrate the potential of LLMs in the context of abstract screening, and then precede with our in-depth discussion on the study’s workflow and design that aims to critically investigate the performance of LLMs in this domain.

Examples of abstract screening by using LLMs

In this subsection, we demonstrate the process of LLM-based abstract screening using ChatGPT with two specified abstracts: (1) Millard et al. [ 24 ] and (2) Zawia et al. [ 25 ]. Using other LLM tools such as Llama, Google PaLM, or Claude for abstract screening is similar and will be skipped for brevity.

In constructing the prompts, we adopted a standardized approach to mimic a typical interaction between a senior researcher and a research assistant. Each prompt was designed to include three critical elements: a brief statement of the topic under review, the exact eligibility criteria as specified in the study guidelines, and the text of the abstract to be reviewed. This approach was designed to simulate a realistic and practical scenario that reflects common academic practices. In addition, to ensure consistency and objectivity in the responses, we required that the results of the LLM be in a binary “yes” or “no” format, directly indicating whether each abstract met the inclusion criteria. This format was chosen to eliminate any ambiguity in the model’s decisions and to facilitate straightforward analysis of its accuracy.

Abstract (1)

ChatGPT prompt: “I would like you to help me with conducting a systematic review on animal depression. I will provide the title and abstract for one journal article and would like you to screen the paper for inclusion. Here are the inclusion criteria: Does the study provide primary data of an animal model of depression or depressive-like phenotype with an appropriate control group? Here is the abstract:

Wistar-Kyoto (WKY) rats show endogenous depressive behavior that can be reversed by antidepressants. Given that WKYs exhibit decreased sensitivity to some antidepressants and treatment-resistant depressed patients often show hypothalamic-pituitary-thyroid (HPT) dysregulation, we examined the behavioral and HPT hormonal responses of WKYs to altered thyroid status. “Euthyroid” WKYs had elevated basal plasma TSH and T(3) levels as compared to Wistars. Hypothyroidism increased TSH levels more in WKYs than in Wistars and increased response latency in the open field test (OFT) of WKYs only. Administration of T(4) and T(3) suppressed plasma TSH equally in both strains. Wistars responded to increased T(3) levels with decreased response latency and increased activity in the OFT, but increased immobility in the forced swim test. In contrast, WKYs responded only to the high T(3) levels with decreased response latency in the OFT. These results suggest the existence of a decreased central nervous system sensitivity to thyroid hormones in WKYs that could be related to their depressive behavior.”

ChatGPT v4 response (accessed on 10/15/2023):

Abstract (2)

The induction of the activity of cerebral ornithine decarboxylase (EC 4.1.1.17) and mRNA by electrical stimulation exhibits regional differences. The effects of the enzyme inhibitor difluoromethylornithine on these regional variations was examined. Administration of this inhibitor resulted in pronounced depression of both basal and induced activity of ornithine decarboxylase in the hippocampus. Basal activity of the enzyme in the neocortex and the cerebellum appeared to be resistant to difluoromethylornithine but the induced enzyme activity was sensitive to the effects of this inhibitor. Susceptibility to difluoromethylornithine may be directly correlated with a slower turnover rate for ornithine decarboxylase. These results suggest that ornithine decarboxylase in the hippocampus may possess a longer half-life than its counterparts in other regions of the brain. Pretreatment with difluoromethylornithine had no effect on the induced ornithine decarboxylase mRNA in the neocortex. Thus, elevated activity of ornithine decarboxylase enzyme, due to electrical stimulation, appears to not have any effect on either the transcription or the decay rate of the induced ornithine decarboxylase mRNA. These findings support the concept of region-specific regulation of cerebral ornithine decarboxylase. ”

From the above two examples presented, it is evident that ChatGPT adeptly comprehends the posed queries and efficiently extracted the inclusion and exclusion criteria. It not only makes clear decisions regarding study inclusion but also articulates its rationale by cross-referencing each criterion.

It is worth noting that the same ChatGPT prompt might result in slightly different responses between different users due to the variability in its response generation, but the conclusion for the eligibility of an abstract is typically consistent. In addition, enhancing the specificity of the criteria within the prompts can further refine the screening process. To illustrate, consider the following enhanced prompts:

Enhanced ChatGPT prompt for abstract (1): “I seek assistance with a systematic review focused on animal depression. I’ll provide the abstract of a particular journal article and would appreciate an assessment for its inclusion based on the following criteria:

The study employs an animal model reflecting depression or a depressive-like phenotype.

It incorporates an appropriate control group.

Primary data is presented within the study.

and here are the exclusion criteria:

The study bypasses the use of an animal model.

The utilized animal model doesn’t characterize depression or a depressive-like phenotype.

Absence of a control group within the study.

The study is primarily a review, devoid of primary data.

Here is the abstract: …”.

With these revised prompts applied to the previously discussed abstracts, the conclusions remain consistent. Nonetheless, we contend that this enhanced structure not only provides a more rigorous framework but also aligns more closely with widely accepted practices in systematic review criteria definition.

Automated workflow for streamlining abstract screening via ChatGPT and other tools

For systematic reviews, particularly when dealing with voluminous data, efficient workflows are paramount. The ChatGPT API (application programming interface) offers a dynamic solution, enabling the automation of abstract screening on a large scale, which circumvents the labor-intensive process of manually inputting abstracts into a chatbot interface. In this subsection, we present an automated workflow for streamlining abstract screening via ChatGPT. Note, though this automated workflow uses ChatGPT as the platform, analogous workflows work for other AI platforms like PaLM, Llama, and Claude.

Automated workflow:

Data collection: The preliminary step entails accumulating a list of titles and abstracts. By utilizing carefully crafted keywords, we retrieve these from PubMed and other pertinent databases. This comprehensive approach ensures the potential inclusion of all relevant studies for a subsequent detailed screening. It is worth noting that while this list is expansive, most of these studies may not find their way into the final meta-analysis post-screening.

Automation through Python: We have devised a python script aimed at harnessing the capabilities of ChatGPT for evaluating the amassed abstracts.

This script interacts with the ChatGPT API (specifically, the GPT-4 version) and, when furnished with tailored prompts, extracts structured responses from ChatGPT.

Typically, the AI’s response commences with a succinct summary, delves into explanations aligned with each criterion, and concludes with a decisive judgment, as exemplified by the examples in the “ Examples of abstract screening by using LLMs ” section.

This automated process efficiently saves ChatGPT’s verdicts on each abstract for ensuing analyses. For instance, it extracts the final decisions regarding the inclusion or exclusion of studies and determines the stance on each pre-specified criterion for every abstract, as exemplified by the last example in the “ Examples of abstract screening by using LLMs ” section.

Additionally, to ascertain the efficiency and cost-effectiveness of this methodology, the script also monitors the time, token usage, and the financial implications of querying the OpenAI API.

In essence, we envision this procedure as delegating the meticulous task of poring over scientific summaries to an AI assistant. This virtual entity meticulously sifts through each summary, determining its alignment with stipulated criteria.

Tuning parameters in the ChatGPT API: The effectiveness of the ChatGPT API is not only dependent on the input data; it is also significantly influenced by adjustable parameters that can refine the responses. Parameters such as temperature, top k, and top p critically affect model performance by modulating the randomness and focus of the output. While fine-tuning these parameters can improve results, it requires significant technical expertise and resources. Defaults, which are rigorously tested by developers, strike a balance between output quality and ease of use, making LLMs more accessible to a wider range of users without the need for complex parameter optimization. While customization holds promise for custom applications, the default settings provide an efficient and practical solution that facilitates wider adoption of LLM technologies.

Given the complexity of fine-tuning these parameters to optimize performance specifically for abstract screening, our study primarily used the recommended default settings for these parameters as provided by the respective platforms (detailed in Table 1 ). This approach was chosen to maintain the feasibility of our experiments and to ensure that our findings are applicable to typical deployment scenarios.

The automated workflow described applies to other LLM tools or different versions of the same tools. Throughout our study, we have tested several popular LLM tools available to us. The specific LLM models and their versions used at the time of our first submission are detailed in Table  1 , along with the tuning parameters.

The field of large language models (LLMs) has evolved rapidly since we started this study in 2023. New models are frequently released, and existing versions are constantly updated. To account for these advances, we have expanded our analysis to include results from the latest versions of previously studied models, as well as a few entirely new ones. As a best practice, we set the temperature parameter to 0 for all latest models. Table 1 now includes these latest models and their versions.

A brief explanation of these parameters is as follows:

Temperature: The temperature controls the randomness of the outputs, with a range from 0 to 2. A temperature value greater than 1 is random and 0 is deterministic. The maximum temperature of 2 gives the most creative and variable outputs.

Max length: The max length is the maximum number of tokens for the model to generate as a response. A single word is generally 2–3 tokens.

Stop sequences: This parameter controls which tokens or phrases will stop the LLM from generating more text.

Top p: When generating text, the model samples from the top p percentage of most likely tokens to generate. The top p is the cumulative probability cutoff for the model’s selection of tokens to generate. Lower top p values mean sampling from a smaller, more top-weighted nucleus.

Top k: When generating text, the model samples from the top k most likely tokens. When deciding the next word to output, the model will select the most likely word when top k is lower.

Frequency penalty: This frequency penalty parameter controls how the LLM penalizes tokens that have already appeared in the input and output text. A frequency penalty of 0 implies that the frequency of the tokens does not impact the LLM and will generate them based on their probability.

Presence penalty: This parameter controls how the LLM penalizes tokens that have not been used recently. A presence penalty of 0 means that the LLM does not care about the recency of the tokens and will generate them based on their probability.

Study design

In our pursuit to assess ChatGPT’s proficiency in abstract screening, we selected certain benchmark databases that have existing performance data from other methodologies. This selection aids in a comparative analysis of performance.

In selecting the systematic reviews for our study, we used a systematic approach guided by specific criteria to ensure relevance and reliability. These studies were selected from the publicly available SYNERGY [ 23 ] dataset, which contains 26 systematic reviews from different disciplines. Key selection criteria included:

Clarity and conciseness of eligibility criteria: The selected studies had well-defined and explicit eligibility criteria. This clarity is essential for accurate replication of the study selection process, which is critical for assessing the performance of LLM tools in an analogous real-world application.

Completeness and cleanliness of data: We ensured that the selected reviews had complete datasets, with all necessary information on included and excluded studies clearly documented, minimizing the risk of ambiguities affecting our analysis.

In addition, to comply with the AMSTAR-2 [ 26 ] guidelines, in particular point 5, we reviewed the methodologies of these reviews to confirm the selection of studies was performed in duplicate and disagreements were resolved by consensus. While our analysis assumes that these systematic reviews adhere to high standards, we recognize the inherent limitations of using pre-existing datasets as a proxy for gold standards in the discussion section.

We picked the following 3 databases from the publicly available SYNERGY dataset [ 23 ]:

Bannach-Brown 2016 [ 27 ]—topic: use of animal models to study depressive behavior

Human-curated (gold standard) results: 1258 excluded abstracts and 230 included abstracts.

We randomly selected 100 excluded abstracts and 100 included abstracts for screening by LLM tools.

Meijboom 2021 [ 28 ]—topic: retransitioning of etanercept in patients with a rheumatic disease

Human-curated (gold standard) results: 599 excluded abstracts and all 32 included abstracts.

We randomly selected 100 excluded abstracts and 32 included abstracts for screening by LLM tools.

Menon 2022 [ 29 ]—topic: methodological rigor of systematic reviews in environmental health

Human-curated (gold standard) results: 896 excluded abstracts and 73 included abstracts.

We randomly selected 100 excluded abstracts and all 73 included abstracts for screening by LLM tools.

For each chosen database, abstracts were categorized as either “cases” (those included based on a gold standard) or “controls” (those excluded per the gold standard). From each category, we randomly selected 100 abstracts (we use all abstracts if there are less than 100 abstracts in that category in a database). These abstracts underwent evaluation by ChatGPT (v4.0) as per our established workflow. Subsequently, ChatGPT’s decisions were juxtaposed against the gold standard to determine sensitivity, specificity, and overall accuracy. The same abstracts were also processed using other LLM tools as listed in Table  1 to record their respective verdicts.

Statistical analysis

To quantify the efficacy of ChatGPT and other AI tools for each database, we calculated the following metrics: (1) sensitivity, (2) specificity, and (3) overall accuracy, where sensitivity is defined as the number of true positives divided by the sum of true positives and false negatives, specificity as the number of true negatives divided by the sum of true negatives and false positives, and accuracy as sum of true positives and true negatives divided by the total number of abstracts. For each metric, associated 95% confidence intervals were also determined. Although it is very common in the field to report F1 score, recall rate, and precision, we believe it is more appropriate to report sensitivity and specificity given this study design. In addition, F1 score, recall rate, and precision can be derived from sensitivity and specificity.

Furthermore, to explore the potential of a unified decision-making process, we combined the decisions from all AI tools using a voting mechanism. The majority decision across the tools was taken as the final verdict for each abstract. For this consolidated approach, we again computed sensitivity, specificity, overall accuracy, and the associated 95% CIs for each database. We also explore the use of latent class analysis (LCA), a model-based clustering approach, to derive consolidated decisions. More details on this LCA approach are provided in the “ Beyond majority voting ” section.

For a given database, 100 cases and 100 controls yield a two-sided 95% confidence interval with a half-width equal to 0.048 when the underline sensitivity (specificity) is approximately 95%.

All statistical analyses were conducted using the R statistical software (version 4.3.1). All tests were two-sided with an alpha level set at 0.05 unless otherwise mentioned.

To improve the transparency and reproducibility of studies using AI tools, we have included the TRIPOD + AI checklist [ 30 ] in our report. This checklist has been adapted to reflect the specifics of our research, which focuses on the evaluation of large language models for abstract screening rather than diagnostic or prognostic modeling. The completed checklist is presented in Table S 1 , to provide readers with a comprehensive overview of our study’s adherence to established reporting standards.

We present the results for each of the 3 databases. For each, we first present the prompts we used when we called LLM tools to screen an abstract, then present the performance data (accuracy, sensitivity, and specificity for each method or LLM tool), followed by a summary of the performance, and a comparison of the performance of the different methods to that based on ChatGPT v4.0.

Results on the Bannach-Brown 2016 database (see Table  2 )

The prompts we used for screening abstracts in this database are as follows:

Conduct a systematic review on animal depression. I provide the title and abstract for one journal article. Provide an overall assessment based on eligibility criteria with only one word answer yes or no with no explanation. Then, for each inclusion or exclusion criterion, answer with only one word, yes if it is included by the inclusion criterion or excluded by the exclusion criterion, and answer no if it does not meet the inclusion criterion or not excluded by the exclusion criterion. After answering all the criteria with yes or no, then provide an overall explanation.

Here is the eligibility criteria: Inclusion Criteria: 1. Any article providing primary data of an animal model of depression or depressive-like phenotype with an appropriate control group (specified above). 2. Animals of all ages, sexes and species, where depression-like phenotype intended to mimic the human condition have been induced. Including animal models where depressive-like phenotypes are induced in the presence of a comorbidity (e.g. obesity or cancer). 3. All studies that claim to model depression or depressive-like phenotypes in animals. Studies that induce depressive behavior or model depression and that also test a treatment or intervention (prior or subsequent to model induction), with no exclusion criteria based on dosage, timing or frequency. 4. Studies measuring behavioral, anatomical and structural, electrophysiological, histological and/or neurochemical outcomes and where genomic, proteomic or metabolomic outcomes are measured in addition to behavioral, anatomical, electrophysiological, histological or neurochemical outcomes. Exclusion Criteria: 1. Review article, editorials, case reports, letters or comments, conference or seminar abstracts, studies providing primary data but not appropriate control group. 2. Human studies and ex vivo, in vitro or in silico studies. Studies will be excluded if authors state an intention to induce or investigate only anxiety or anxious behavior. Studies will be excluded if there is no experimental intervention on the animals (e.g. purely observational studies). 3. Studies that investigate treatments or interventions, but no depressive behavior or model of depression is induced (e.g. toxicity and side-effect studies). 4. Where metabolic outcome measures are the primary outcome measure of a study. Where genomic, proteomic, metabolic or metabolomic outcomes are the sole outcome measures in a study, they will be excluded.

Here is the abstract:

Among all the LLM tools we tested, ChatGPT v4.0 stood out with the highest accuracy (0.945) and specificity (0.960), and satisfactory sensitivity (0.930). Combined decision using major voting seemed to improve sensitivity (0.970) considerably but did not improve specificity (0.870) much. Comparatively, the zero-shot method was less effective across these metrics, while the hybrid method attained superior accuracy (0.961) and specificity (0.982), albeit with reduced sensitivity (0.843). We acknowledge that our findings regarding the zero-shot and hybrid methods differ from those reported in [ 18 ] for the same set of abstracts. This discrepancy could be attributed to the use of distinct sets of embeddings in our analysis compared to the previous study.

For this database, the newer versions of ChatGPT (3.5-Turbo and 4-Turbo) did not improve performance over ChatGPT (v4.0). Gemini-1.0-pro (vs. PaLM 2) and Llama 3 (vs. Llama 2) improved over their older versions, but did not surpass the performance of ChatGPT (v4.0). Claude 3 performed well, but still did not surpass the performance of ChatGPT (v4.0).

Comparison between LLM tools. We compared the performance (sensitivity and specificity) between ChatGPTv4.0 and other LLM tools using the McNemar test and found that ChatGPTv4.0 performed significantly better ( p value = 0.002) than Google PaLM 2 in terms of sensitivity; ChatGPTv4.0 performed significantly better than ChatGPTv3.5 ( p value = 0.008) and better than Llama-2 ( p value < 0.001) in terms of specificity. Combining the decisions of different LLM tools using majority voting did not improve the overall accuracy compared to ChatGPTv4.0. Specifically, there was no statistically significant difference ( p value = 0.134) in sensitivity between the combined decision (majority voting) and ChatGPTv4.0, and the combined decision was significantly worse ( p value = 0.008) than ChatGPTv4.0 in terms of specificity.

Comparison between ChatGPT v4.0 and zero-shot and hybrid methods: We assessed the performance (sensitivity and specificity) of ChatGPT v4.0 against both the zero-shot and hybrid approaches using the McNemar test. Specifically, we aligned the screening results from 100 cases and 100 controls as per the ChatGPT v4.0 method and similarly for the zero-shot and hybrid methods, testing for inconsistencies between these approaches as previously done. Our analysis revealed that ChatGPT v4.0 significantly outperformed the zero-shot method in sensitivity ( p value < 0.001) but showed comparable effectiveness in specificity ( p value = 0.37). Additionally, ChatGPT v4.0 demonstrated marginally superior sensitivity compared to the hybrid method ( p value = 0.07), while its performance in specificity was similar ( p value = 1.00).

Results on the Meijboom 2021 database (see Table  3 )

Conduct a systematic review on transitioning patients from an originator to a corresponding biosimilar.

I provide the title and abstract for one journal article. Provide an overall assessment based on eligibility criteria with only one word answer yes or no, with no explanation. Then, for each inclusion or exclusion criterion, answer with only one word, yes if it is included by the inclusion criterion or excluded by the exclusion criterion, and answer no if it does not meet the inclusion criterion or not excluded by the exclusion criterion.

After answering all the criteria with yes or no, then provide an overall explanation.

Here is the eligibility criteria:

Articles were included if they met the following criteria:

Study involved transitioning from a TNFα inhibitor (including etanercept, infliximab, and adalimumab) originator to a biosimilar

The number of patients who retransitioned was reported or could be calculated

The article was an original research article published in a peer-reviewed journal

The article included baseline characteristics of the patients who transitioned

The article was written in English

The full-text version of the article could be obtained.

Transitioning was defined as patients in whom the biosimilar was introduced after the originator, without treatment with other drugs in between. Retransitioning was defined as restarting the originator directly after discontinuing a biosimilar, without treatment with other drugs in between. In summary, transitioning was defined as switching from the originator to a biosimilar; retransitioning was defined as switching from the originator to a biosimilar and back to the originator. Both transitioning and retransitioning involved changes with the same active biological substance.

Among all the LLM tools we tested, ChatGPT v4.0 stood out with the highest accuracy (0.840), but not with specificity (0.860) or satisfactory sensitivity (0.812). Compared to ChatGPTv4.0, combined decision using major voting did not improve overall accuracy (0.720), but improved sensitivity (1.000) at the sacrifice of specificity (0.630).

Comparison between LLM tools. We compared the performance (sensitivity and specificity) between ChatGPTv4.0 and other LLM tools using the McNemar test and found that ChatGPTv4.0 performed significantly better ( p value < 0.001) than Google PaLM 2, but significantly worse than ChatGPT3.5 ( p value = 0.001) and Llama 2 in terms of sensitivity; ChatGPTv4.0 performed significantly better than ChatGPTv3.5 ( p value < 0.001) and better than Llama 2 ( p value < 0.001), but worse than Google PaLM 2 ( p value = 0.002), in terms of specificity. Combining the decisions of different LLM tools using majority voting did not improve the overall accuracy compared to ChatGPTv4.0. Specifically, there was statistically significant difference ( p value = 0.008) in sensitivity between the combined decision (majority voting) and ChatGPTv4.0, and the combined decision was not significantly worse ( p value > 0.50) than ChatGPTv4.0 in terms of specificity.

For this database, the newer versions of ChatGPT (3.5-Turbo and 4-Turbo) did not improve performance over ChatGPT (v4.0), and Gemini-1.0-pro (vs. PaLM 2) did not improve performance either. However, Llama 3 (vs. Llama 2) improved over its older version and surpassed the performance of ChatGPT (v4.0). Claude 3 also slightly surpassed the performance of ChatGPT (v4.0).

Comparison between ChatGPT v4.0 and zero-shot and hybrid methods: We evaluated the performance of ChatGPT v4.0, focusing on sensitivity and specificity, in comparison with the zero-shot and hybrid approaches, employing the McNemar test as described above. In this analysis, we aligned the screening results from 32 cases and 100 controls for the tests. Our findings indicated that ChatGPT v4.0 significantly surpassed the zero-shot method in sensitivity ( p value = 0.0002) and exhibited marginally improved specificity ( p value = 0.099). Furthermore, ChatGPT v4.0 showed notably higher sensitivity than the hybrid method ( p value < 0.001), although its specificity was comparatively lower.

Results on the Menon 2022 database (see Table  4 )

“Conduct a systematic review on the methodological rigour of systematic reviews in environmental health.

I provide the title and abstract for one journal article.

Provide an overall assessment based on eligibility criteria with only one word answer yes or no, with no explanation.

Then, for each inclusion or exclusion criterion, answer with only one word, yes if it is included by the inclusion criterion or excluded by the exclusion criterion and answer no if it does not meet the inclusion criterion or not excluded by the exclusion criterion.

Here are the eligibility criteria:

To be eligible for inclusion in the SR sample, documents had to fulfill the following criteria:

Identify explicitly as a “systematic review” in their title

Assess the effect of a non-acute, non-communicable, environmental exposure on a health outcome. Environmental exposures can include air and water pollutants, radiation, noise, occupational hazards, lifestyle factors (like diet or physical activity) and lifestyle choices influenced by family and peers (like substance use), social and economic factors (like stress from work or living conditions).

Include studies in people or mammalian models

Be available in HTML format

Abstract X”

Among all the LLM tools we tested, ChatGPT v4.0 stood out with the highest accuracy (0.913) and specificity (0.932), but not with specificity (0.900). Compared to ChatGPTv4.0, combined decision using major voting did not improve overall accuracy (0.884) or sensitivity (0.808), but improved specificity (0.940).

Comparison between LLM tools. We compared the performance (sensitivity and specificity) between ChatGPTv4.0 and other LLM tools using the McNemar test and found that ChatGPTv4.0 performed significantly better than ChatGPT3.5 ( p value < 0.001), Google PaLM 2, and Llama 2 ( p value = 0.02) in terms of sensitivity; ChatGPTv4.0 performed worse than ChatGPTv3.5 and Google PaLM 2, in terms of specificity. Combining the decisions of different LLM tools using majority voting did not improve the overall accuracy compared to ChatGPTv4.0. Specifically, there was statistically significant difference ( p value = 0.008) in sensitivity between the combined decision (majority voting) and ChatGPTv4.0, and the combined decision was not significantly different ( p value = 0.134) than ChatGPTv4.0 in terms of specificity.

For this database, the newer versions of ChatGPT (3.5-Turbo and 4-Turbo) did not improve performance over ChatGPT (v4.0). However, both Gemini-1.0-pro (vs. PaLM 2) and Llama 3 (vs. Llama 2) improved over their older versions and surpassed the performance of ChatGPT (v4.0). Claude 3 also performed well but did not surpass the performance of ChatGPT (v4.0).

Comparison between ChatGPT v4.0 and zero-shot and hybrid methods: We aligned the screening results from 73 cases and 100 controls based on the ChatGPT v4.0 method, and similarly for the zero-shot and hybrid methods, to test for inconsistencies between these approaches, using the McNemar test as done in previous assessments. Our analysis showed that ChatGPT v4.0 significantly outperformed the zero-shot method in both sensitivity ( p value < 0.001) and specificity ( p value = 0.016). In comparison with the hybrid method, ChatGPT v4.0 also demonstrated superior sensitivity ( p value < 0.001) and better specificity ( p value = 0.04).

Monetary cost and time cost

To use the ChatGPT API or other LLM tools, the owners of these platforms charge a predetermined rate for access to the corresponding APIs. These fees are calculated in USD per thousand tokens, where tokens are the basic units used by these LLM platforms to quantify text length. In this context, a token can represent a word, a punctuation mark, or a character. The financial cost of screening 200 abstracts was approximately $6 for ChatGPT v4.0, $0.2 for ChatGPT v3.5, $10 for Llama 2 (using Replicate), while Google PaLM 2 offered its services for free to invited developers. Thus, the cumulative cost of evaluating 200 abstracts across all platforms was approximately $16.2. The cumulative cost of evaluating 200 abstracts across all latest models ($3 for GPT-4-Turbo, $0.05 for GPT-3.5-Turbo, free for Gemini-1.0-pro, $0.05 for Llama-3, $4 for Claude) was less, approximately $7.1. In terms of time efficiency, processing 200 abstracts with each of these LLM tools took approximately 10–20 min using a single thread. However, it is imperative to recognize that abstract screening lends itself well to parallelization. Consequently, one could significantly speed up the process by setting up multiple threads to simultaneously screen different subsets of abstracts, thereby reducing the overall time required for completion. This parallel approach not only increases efficiency, but also ensures that large amounts of data can be processed in a timely manner, making LLM tools even more attractive for large-scale abstract screening tasks. In summary, the monetary and time costs of using LLM tools for abstract screening are negligible compared to manual labeling.

Beyond majority voting

We have expanded our analysis to include a variety of approaches for synthesizing decisions across different LLM tools. Our methodology is inspired by the concept of combining multiple diagnostic tests in the absence of a gold standard, akin to situations where human expert consensus is not available. There are several publications discussing such scenarios [ 31 , 32 ], among which we proposed to use the latent class analysis (LCA) models.

Latent class analysis (LCA) is a statistical method used to identify subgroups within a population, which are not directly observed (hence “latent”) [ 33 , 34 , 35 ]. It is particularly useful when the research interest lies in categorizing individuals into mutually exclusive groups based on their responses to multiple observed variables. In the context of abstract screening, LCA can offer a sophisticated means of integrating decisions from different LLM tools without relying on a gold standard, typically provided by human expert consensus. This approach assumes that the unobserved subgroups (or “latent classes”) explain the dependence between the observed decisions made by each of the LLM tools.

Utilizing the LCA model, we treat the decisions from all LLM tools as dichotomous variables, corresponding to the adherence to each inclusion or exclusion criterion, as well as the overall decision. For instance, within the Bannach-Brown 2016 database (BB2016), there are eight criteria in total with four criteria each for inclusion and exclusion and one overall decision for inclusion, resulting in a total of nine binary items per LLM tool. In our analysis, we incorporated decisions from GPT v4.0, v3.5, and Llama 2. Decisions from Google PaLM 2 were excluded due to a high frequency (10% or more) of incomplete responses. Consequently, for the Bannach-Brown 2016 database, we worked with 27 binary items. For other databases such as Meijboom 2021 (Mj2021) and Menon 2022 (Me2022), the binary items totaled 21 and 15, respectively. It is important to note that LCA models were fitted to the binary data of each database independently.

The LCA model fitting process enables us to calculate the posterior probabilities of each abstract belonging to specific latent classes or subgroups. Abstracts are then categorized based on these probabilities, with assignment to the class for which an abstract has the highest posterior membership probability. The determination of the number of latent classes is a critical step in the LCA model fitting, which requires a priori specification. In our evaluation, we explored models with class numbers ranging from 2 to 6 and utilized the Bayesian information criterion (BIC) to identify the most “optimal” LCA model for our datasets.

Table 5 shows that after applying the Bayesian information criterion (BIC) to determine the most appropriate model for our data, we identified a 3-class model as the best fit for the binary decisions derived from the BB2016 database. Similarly, a 4-class model was optimal for the Mj2021 database, while a 3-class model was again best for the Me2022 database. The confusion matrices generated by the selected LCA models for each database provided a clear juxtaposition between the LLM-assigned classes and the actual labels of the abstracts (see Table  6 ).

The performance metrics derived from these models are noteworthy. For the BB2016 database, should we categorize abstracts within class with label 2 as “included” and assign the others in classes with label 1 or 3 to the “excluded” category, the LCA model achieved a sensitivity rate of 93% and a specificity rate of 96%, indicating a high degree of accuracy in classifying relevant and irrelevant abstracts. In the case of the Mj2021 database, if we view class 1 as “included” group and classes 2 and 3 as “excluded” group, the model achieved a perfect sensitivity rate of 100%, meaning that it correctly identified all relevant abstracts, although the specificity was lower at 79%, indicating a higher rate of false positives. Similarly, for the Me2022 database, considering class 1 to be the “excluded” category and classes 2 and 3 to be the “included” group, the model showed a sensitivity of 94.5% and a specificity of 83%, a good balance between identifying relevant abstracts and avoiding false inclusions.

These results highlight the robustness of the latent class analysis approach to the abstract screening task, providing an effective method for classifying abstracts when a gold standard is not available. The varying levels of sensitivity and specificity across databases underscore the need to tailor the LCA model to the specific characteristics of each dataset as well as further future research.

We have incorporated results from the latest LLM models to increase the robustness and relevance of our findings. However, to maintain consistency and comparability with our original analyses, we have not incorporated these new results into the previously established majority voting or latent class analysis (LCA) approaches. Instead, we have chosen to make all raw data, including results from these newer models, freely available in our GitHub repository. This approach allows interested researchers and practitioners to conduct further investigations or apply alternative methods of analysis. By providing access to this additional data, we aim to promote transparency and enable the broader community to engage with and potentially build upon our work.

This study began with a rigorous exploration of the capabilities of large language models (LLMs) in abstract screening. We used automation scripts developed in Python to interact with the APIs of several LLM tools, including Chat GPT v4.0, Google PaLM 2, and Meta Llama 2, as well as latest versions of these tools. Our central goal was to evaluate the efficiency and accuracy of these tools across three different databases of abstracts, leading us to a complex understanding of their potential in this context.

Large language models (LLMs), particularly ChatGPT, have garnered global attention since their inception. Employing LLMs for abstract screening in systematic reviews is an innovative concept [ 32 , 33 ] and remains underexplored. This study presents the first comprehensive evaluation of LLMs applied to systematic review processes. The findings are encouraging, suggesting that LLMs could revolutionize abstract screening. Specifically, ChatGPT v4.0 exhibited stellar performance across three test scenarios, achieving an accuracy of at least 85%. Furthermore, it attained sensitivity and specificity rates ranging from 80% to an impressive 95%. These exceptional outcomes highlight the substantial promise of LLMs in abstract screening, offering an efficient and capable alternative to the conventional, laborious approaches that typically necessitate extensive human annotation.

However, it is important to acknowledge that we are still in the early stages of integrating LLM tools into the abstract screening field, and they are not without their imperfections—for example, occasionally excluding many (20%) relevant studies, even with the best-performed LLM tools, ChatGPT v4.0. These tools are not a universal solution to all the challenges associated with abstract screening, and they are not ready to completely replace human expertise in this area. Instead, they should be embraced as invaluable assistants in the abstract screening process.

In discussing the limitations of our study, it is important to recognize the constraints associated with our dataset selection and model configuration. We used only three databases from the SYNERGY set, limiting the generalizability of our findings across disciplines and datasets. In addition, the reliance on human-curated labels as a gold standard, while necessary, introduces potential biases due to the retrospective nature of our analysis. These labels may contain errors, and the methodology used in the original reviews to resolve discrepancies may affect the validity of our conclusions.

The parameters chosen for our LLMs—temperature, top k, top p, and prompts—were set to defaults or based on natural conversations to balance output quality with ease of use. While this approach minimizes the need for technical expertise, it may not be optimal for all screening scenarios. In addition, the reliance of LLMs on abstracts alone, as opposed to full-text evaluations, presents a fundamental challenge; critical data influencing inclusion or exclusion may not be present in the abstracts, potentially compromising screening accuracy.

In addition, the rapid development of LLMs and their “black box” nature pose challenges to the transparency that is essential in scientific settings. The environmental impact of using these computationally intensive models is also significant [ 36 ], requiring sustainability considerations. Future research should focus on refining these tools to increase transparency and efficiency, and ensure their responsible development and use in systematic reviews.

Our research suggests that LLM tools are ready to take on a role in abstract screening and are poised to have an immediate and positive impact on the process. Their integration into abstract screening can manifest itself in a few ways. They can serve as autonomous AI reviewers, adding an extra layer of scrutiny and ensuring thoroughness. Our findings suggest that a collective decision, such as one derived from majority voting, can sometimes improve sensitivity, underscoring the potential of LLM tools as a reliable safeguard against oversight, ensuring both comprehensiveness and accuracy.

In addition, LLM tools can facilitate a synergistic partnership with human experts. They are adept at identifying “high-risk” abstracts where different LLM tools have reached different judgments, flagging them for further human evaluation, and promoting a careful and error-free screening process while minimizing human effort.

Another exciting prospect is the integration of LLM tools with hybrid approaches and active learning approach. In this scenario, LLM tools could autonomously annotate abstracts in the training set, minimizing the need for human labeling. Subsequently, these labeled abstracts could be used to train custom NLP models, paving the way for a streamlined and efficient abstract screening process, resulting in significant time and resource savings. Further research is needed to understand how the “uncertainty” in LLM-based decisions, when human-curated labels are not used, affects the performance of the hybrid approach. We also note from the test examples that the performance of hybrid approaches varies widely from example to example and depending on the text embedding tools used. Extensive research is needed to perfect the hybrid approaches.

Another future research direction is to explore how to fine-tune different versions of LLM tools and how to derive collective decisions. One idea is that by using different tuning parameters, one could propose different versions of LLM tools, and if they perform similarly in terms of accuracy but give different decisions (e.g., not highly correlated), we expect that better collective decisions would be obtained, as observed in many ensemble learning experiences [ 37 ]. However, this could be costly and require a lot of exploration.

More importantly, it would be particularly valuable to prospectively test these LLM tools, or integration of these tools with other approaches like zero-shot, active learning, in real-world meta-analysis and systematic review projects. This would provide deeper insights into their practical utility and effectiveness, and a more comprehensive understanding of their impact in live research environments.

In summary, while LLM tools may not be able to fully replace human experts in abstract screening, their ability to transform the screening process is both undeniable and imminent. With continued advances in technology and ongoing refinement, these tools will play a critical role in the future of abstract screening, ushering in a new era of efficiency and effectiveness.

Availability of data and materials

The datasets analyzed during the current study are available in the SYNERGY repository, https://github.com/asreview/synergy-dataset . We have created a GitHub repository https://github.com/mikeli380/LLMAbstractScreening to host our code (R/Python), abstracts, and intermediate results so that interested readers can replicate our findings.

Higgins JPT, et al. Cochrane handbook for systematic reviews of interventions. 2019.

Book   Google Scholar  

Moher D, et al. Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. PLoS Med. 2009;6(7). https://doi.org/10.1371/journal.pmed.1000097 .

Sackett DL, Rosenberg WMC, Gray JAM, Haynes RB,  Richardson WS. Evidence based medicine: what it is and what it isn’t. 1996. Clin Orthop Relat Res. 2007;455.  https://doi.org/10.1136/bmj.312.7023.71 .

Lavis JN, Posada FB, Haines PA, Osei E. Use of research to inform public policymaking. Lancet. 2004;364(9445). https://doi.org/10.1016/S0140-6736(04)17317-0 .

Bastian H, Glasziou P,  Chalmers I. Seventy-five trials and eleven systematic reviews a day: how will we ever keep up?. PLoS Med. 2010;7(9).   https://doi.org/10.1371/journal.pmed.1000326 .

Polanin JR, Pigott TD, Espelage DL, Grotpeter JK. Best practice guidelines for abstract screening large-evidence systematic reviews and meta-analyses. Res Synth Methods. 2019;10(3). https://doi.org/10.1002/jrsm.1354 .

Turner EH, Matthews AM, Linardatos E, Tell RA, Rosenthal R. Selective publication of antidepressant trials and its influence on apparent efficacy. N Engl J Med. 2008;358(3). https://doi.org/10.1056/nejmsa065779 .

Edwards P, Clarke M, DiGuiseppi C, Pratap S, Roberts I, Wentz R. Identification of randomized controlled trials in systematic reviews: accuracy and reliability of screening records. Stat Med. 2002;21(11). https://doi.org/10.1002/sim.1190 .

Wang Z, Nayfeh T, Tetzlaff J, O’Blenis P, Murad MH. Error rates of human reviewers during abstract screening in systematic reviews. PLoS ONE. 2020;15(1). https://doi.org/10.1371/journal.pone.0227742 .

O’Mara-Eves A, Thomas J, McNaught J, Miwa M, Ananiadou S. Using text mining for study identification in systematic reviews: a systematic review of current approaches. Syst Rev. 2015;4(1). https://doi.org/10.1186/2046-4053-4-5 .

OpenAI. Introducing ChatGPT Plus. OpenAI Blog; 2023. https://openai.com/blog/chatgpt-plus . Accessed 8 Nov 2023.

Google DeepMind. Introducing PaLM 2. Google Blog; 2023.  https://blog.google/technology/ai/google-palm-2-ai-large-language-model/ . Accessed 8 Nov 2023.

Meta AI Research. Meta and Microsoft introduce the next generation of Llama. Facebook AI Blog; 2023. https://ai.meta.com/blog/llama-2/ . Accessed 8 Nov 2023.

Claude.ai. Claude AI API reference. 2024. https://docs.anthropic.com/en/api/getting-started . Accessed 4 Jun 2024.

Wallace BC, Small K, Brodley CE, Lau J, Trikalinos TA. Deploying an interactive machine learning system in an evidence-based practice center: Abstrackr. 2012. https://doi.org/10.1145/2110363.2110464 .

Alshami A, Elsayed M, Ali E, Eltoukhy AEE, Zayed T. Harnessing the power of ChatGPT for automating systematic review process: methodology, case study, limitations, and future directions. Systems. 2023;11(7). https://doi.org/10.3390/systems11070351 .

Qureshi R, Shaughnessy D, Gill KAR, Robinson KA, Li T, Agai E. Are ChatGPT and large language models ‘the answer’ to bringing us closer to systematic review automation?  Syst Rev. 2023;12(1).   https://doi.org/10.1186/s13643-023-02243-z .

Xian Y, Lampert CH, Schiele B, Akata Z. Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans Pattern Anal Mach Intell. 2019;41(9). https://doi.org/10.1109/TPAMI.2018.2857768 .

Moreno-Garcia CF, Jayne C, Elyan E, Aceves-Martins M. A novel application of machine learning and zero-shot classification methods for automated abstract screening in systematic reviews. Decis Anal J. 2023;6.  https://doi.org/10.1016/j.dajour.2023.100162 .

Ferdinands G, et al. Performance of active learning models for screening prioritization in systematic reviews: a simulation study into the Average Time to Discover relevant records. Syst Rev. 2023;12(1). https://doi.org/10.1186/s13643-023-02257-7 .

Boetje J, van de Schoot R. The SAFE procedure: a practical stopping heuristic for active learning-based screening in systematic reviews and meta-analyses. Syst Rev. 2024;13(1). https://doi.org/10.1186/s13643-024-02502-7 .

Yang Y, Loog M. A benchmark and comparison of active learning for logistic regression. Pattern Recognit. 2018;83. https://doi.org/10.1016/j.patcog.2018.06.004 .

De Bruin RJ, Ma Y, Ferdinands G, Teijema J, Van de Schoot. SYNERGY - open machine learning dataset on study selection in systematic reviews. DataverseNL; 2023. https://dataverse.nl/dataset.xhtml?persistentId=doi:10.34894/HE6NAQ .

Millard SJ, Weston-Green K, Newell KA. The Wistar-Kyoto rat model of endogenous depression: a tool for exploring treatment resistance with an urgent need to focus on sex differences. Prog Neuropsychopharmacol Biol Psychiatry. 2020;101. https://doi.org/10.1016/j.pnpbp.2020.109908 .

Zawia NH, Mattia CJ, Bondy SC. Differential effects of difluoromethylornithine on basal and induced activity of cerebral ornithine decarboxylase and mRNA. Neuropharmacology. 1991;30(4). https://doi.org/10.1016/0028-3908(91)90058-J .

Shea BJ, et al. AMSTAR 2: a critical appraisal tool for systematic reviews that include randomised or non-randomised studies of healthcare interventions, or both. BMJ. 2017;358. https://doi.org/10.1136/bmj.j4008 .

Bannach-Brown A, Liao J, Wegener G, Macleod M. Understanding in vivo modelling of depression in non-human animals: a systematic review protocol. Evid Based Preclin Med. 2016;3(2). https://doi.org/10.1002/ebm2.24 .

Meijboom RW, Gardarsdottir H, Becker ML, ten Wolde S, Egberts TCG, Giezen TJ. Incidence of and reasons and determinants associated with retransitioning from biosimilar etanercept to originator etanercept. BioDrugs. 2021;35(6). https://doi.org/10.1007/s40259-021-00501-x .

Menon JML, Struijs F, Whaley P. The methodological rigour of systematic reviews in environmental health. Crit Rev Toxicol. 2022;52(3). https://doi.org/10.1080/10408444.2022.2082917 .

Collins GS, et al. Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence. BMJ Open. 2021;11(7). https://doi.org/10.1136/bmjopen-2020-048008 .

Joseph L, Gyorkos TW, Coupal L. Bayesian estimation of disease prevalence and the parameters of diagnostic tests in the absence of a gold standard. Am J Epidemiol. 1995;141(3). https://doi.org/10.1093/oxfordjournals.aje.a117428 .

Hui SL, Walter SD. Estimating the error rates of diagnostic tests. Biometrics. 1980;36(1). https://doi.org/10.2307/2530508 .

Dendukuri N, Joseph L. Bayesian approaches to modeling the conditional dependence between multiple diagnostic tests. Biometrics. 2001;57(1). https://doi.org/10.1111/j.0006-341X.2001.00158.x .

Collins LM, Lanza ST. Latent class and latent transition analysis: with applications in the social, behavioral, and health sciences. 2010.

Google Scholar  

McCutcheon AL. Latent class analysis. Newbury Park: Sage; 1987.

Rillig MC, Ågerstrand M, Bi M, Gould KA, Sauerland U. Risks and benefits of large language models for the environment. Environm Sci Technol. 2023;57(9). https://doi.org/10.1021/acs.est.3c01106 .

Sagi O, Rokach L. Ensemble learning: a survey.  Wiley Interdiscip Rev Data Min Knowl Discov. 2018;8(4). https://doi.org/10.1002/widm.1249 .

Download references

Acknowledgements

The authors thank the reviewers and the Editor for their insightful comments and suggestions, which have greatly improved the quality of this work.

Not applicable.

Author information

Authors and affiliations.

Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA

Michael Li & Xianming Tan

Department of Mathematics and Statistics, University of North Carolina at Greensboro, Greensboro, NC, 27402, USA

Jianping Sun

Department of Biostatistics and Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA

Xianming Tan

You can also search for this author in PubMed   Google Scholar

Contributions

XT conceived the paper. ML and XT devised the study. ML, JS, and XT analyzed the datasets. ML, JS, and XT wrote the manuscript. All authors edited and approved the final manuscript.

Corresponding author

Correspondence to Xianming Tan .

Ethics declarations

Ethics approval and consent to participate, competing interests.

The authors declare that they have no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Supplementary material 1: table s1. tripod + ai checklist., rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/ .

Reprints and permissions

About this article

Cite this article.

Li, M., Sun, J. & Tan, X. Evaluating the effectiveness of large language models in abstract screening: a comparative analysis. Syst Rev 13 , 219 (2024). https://doi.org/10.1186/s13643-024-02609-x

Download citation

Received : 20 December 2023

Accepted : 11 July 2024

Published : 21 August 2024

DOI : https://doi.org/10.1186/s13643-024-02609-x

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Abstract screening
• Automated text analysis
• Google PaLM

Systematic Reviews

ISSN: 2046-4053

• Submission enquiries: Access here and click Contact Us
• General enquiries: [email protected]

• UWF Libraries

Literature Review: Conducting & Writing

• Sample Literature Reviews
• Steps for Conducting a Lit Review
• Finding "The Literature"
• Organizing/Writing
• APA Style This link opens in a new window
• Chicago: Notes Bibliography This link opens in a new window
• MLA Style This link opens in a new window

Sample Lit Reviews from Communication Arts

Have an exemplary literature review.

• Literature Review Sample 1
• Literature Review Sample 2
• Literature Review Sample 3

Have you written a stellar literature review you care to share for teaching purposes?

Are you an instructor who has received an exemplary literature review and have permission from the student to post?

Please contact Britt McGowan at [email protected] for inclusion in this guide. All disciplines welcome and encouraged.

• << Previous: MLA Style
• Next: Get Help! >>
• Last Updated: Aug 8, 2024 11:00 AM
• URL: https://libguides.uwf.edu/litreview

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, generate accurate citations for free.

• Knowledge Base

Methodology

• How to Write a Literature Review | Guide, Examples, & Templates

How to Write a Literature Review | Guide, Examples, & Templates

Published on January 2, 2023 by Shona McCombes . Revised on September 11, 2023.

What is a literature review? A literature review is a survey of scholarly sources on a specific topic. It provides an overview of current knowledge, allowing you to identify relevant theories, methods, and gaps in the existing research that you can later apply to your paper, thesis, or dissertation topic .

There are five key steps to writing a literature review:

• Search for relevant literature
• Evaluate sources
• Identify themes, debates, and gaps
• Outline the structure
• Write your literature review

A good literature review doesn’t just summarize sources—it analyzes, synthesizes , and critically evaluates to give a clear picture of the state of knowledge on the subject.

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

What is the purpose of a literature review, examples of literature reviews, step 1 – search for relevant literature, step 2 – evaluate and select sources, step 3 – identify themes, debates, and gaps, step 4 – outline your literature review’s structure, step 5 – write your literature review, free lecture slides, other interesting articles, frequently asked questions, introduction.

• Quick Run-through
• Step 1 & 2

When you write a thesis , dissertation , or research paper , you will likely have to conduct a literature review to situate your research within existing knowledge. The literature review gives you a chance to:

• Demonstrate your familiarity with the topic and its scholarly context
• Develop a theoretical framework and methodology for your research
• Position your work in relation to other researchers and theorists
• Show how your research addresses a gap or contributes to a debate
• Evaluate the current state of research and demonstrate your knowledge of the scholarly debates around your topic.

Writing literature reviews is a particularly important skill if you want to apply for graduate school or pursue a career in research. We’ve written a step-by-step guide that you can follow below.

Receive feedback on language, structure, and formatting

Professional editors proofread and edit your paper by focusing on:

• Academic style
• Vague sentences
• Style consistency

See an example

Writing literature reviews can be quite challenging! A good starting point could be to look at some examples, depending on what kind of literature review you’d like to write.

• Example literature review #1: “Why Do People Migrate? A Review of the Theoretical Literature” ( Theoretical literature review about the development of economic migration theory from the 1950s to today.)
• Example literature review #2: “Literature review as a research methodology: An overview and guidelines” ( Methodological literature review about interdisciplinary knowledge acquisition and production.)
• Example literature review #3: “The Use of Technology in English Language Learning: A Literature Review” ( Thematic literature review about the effects of technology on language acquisition.)
• Example literature review #4: “Learners’ Listening Comprehension Difficulties in English Language Learning: A Literature Review” ( Chronological literature review about how the concept of listening skills has changed over time.)

You can also check out our templates with literature review examples and sample outlines at the links below.

Download Word doc Download Google doc

Before you begin searching for literature, you need a clearly defined topic .

If you are writing the literature review section of a dissertation or research paper, you will search for literature related to your research problem and questions .

Make a list of keywords

Start by creating a list of keywords related to your research question. Include each of the key concepts or variables you’re interested in, and list any synonyms and related terms. You can add to this list as you discover new keywords in the process of your literature search.

• Social media, Facebook, Instagram, Twitter, Snapchat, TikTok
• Body image, self-perception, self-esteem, mental health
• Generation Z, teenagers, adolescents, youth

Search for relevant sources

Use your keywords to begin searching for sources. Some useful databases to search for journals and articles include:

• Your university’s library catalogue
• Google Scholar
• Project Muse (humanities and social sciences)
• Medline (life sciences and biomedicine)
• EconLit (economics)
• Inspec (physics, engineering and computer science)

You can also use boolean operators to help narrow down your search.

Make sure to read the abstract to find out whether an article is relevant to your question. When you find a useful book or article, you can check the bibliography to find other relevant sources.

You likely won’t be able to read absolutely everything that has been written on your topic, so it will be necessary to evaluate which sources are most relevant to your research question.

For each publication, ask yourself:

• What question or problem is the author addressing?
• What are the key concepts and how are they defined?
• What are the key theories, models, and methods?
• Does the research use established frameworks or take an innovative approach?
• What are the results and conclusions of the study?
• How does the publication relate to other literature in the field? Does it confirm, add to, or challenge established knowledge?
• What are the strengths and weaknesses of the research?

Make sure the sources you use are credible , and make sure you read any landmark studies and major theories in your field of research.

You can use our template to summarize and evaluate sources you’re thinking about using. Click on either button below to download.

Take notes and cite your sources

As you read, you should also begin the writing process. Take notes that you can later incorporate into the text of your literature review.

It is important to keep track of your sources with citations to avoid plagiarism . It can be helpful to make an annotated bibliography , where you compile full citation information and write a paragraph of summary and analysis for each source. This helps you remember what you read and saves time later in the process.

Prevent plagiarism. Run a free check.

To begin organizing your literature review’s argument and structure, be sure you understand the connections and relationships between the sources you’ve read. Based on your reading and notes, you can look for:

• Trends and patterns (in theory, method or results): do certain approaches become more or less popular over time?
• Themes: what questions or concepts recur across the literature?
• Debates, conflicts and contradictions: where do sources disagree?
• Pivotal publications: are there any influential theories or studies that changed the direction of the field?
• Gaps: what is missing from the literature? Are there weaknesses that need to be addressed?

This step will help you work out the structure of your literature review and (if applicable) show how your own research will contribute to existing knowledge.

• Most research has focused on young women.
• There is an increasing interest in the visual aspects of social media.
• But there is still a lack of robust research on highly visual platforms like Instagram and Snapchat—this is a gap that you could address in your own research.

There are various approaches to organizing the body of a literature review. Depending on the length of your literature review, you can combine several of these strategies (for example, your overall structure might be thematic, but each theme is discussed chronologically).

Chronological

The simplest approach is to trace the development of the topic over time. However, if you choose this strategy, be careful to avoid simply listing and summarizing sources in order.

Try to analyze patterns, turning points and key debates that have shaped the direction of the field. Give your interpretation of how and why certain developments occurred.

If you have found some recurring central themes, you can organize your literature review into subsections that address different aspects of the topic.

For example, if you are reviewing literature about inequalities in migrant health outcomes, key themes might include healthcare policy, language barriers, cultural attitudes, legal status, and economic access.

Methodological

If you draw your sources from different disciplines or fields that use a variety of research methods , you might want to compare the results and conclusions that emerge from different approaches. For example:

• Look at what results have emerged in qualitative versus quantitative research
• Discuss how the topic has been approached by empirical versus theoretical scholarship
• Divide the literature into sociological, historical, and cultural sources

Theoretical

A literature review is often the foundation for a theoretical framework . You can use it to discuss various theories, models, and definitions of key concepts.

You might argue for the relevance of a specific theoretical approach, or combine various theoretical concepts to create a framework for your research.

Like any other academic text , your literature review should have an introduction , a main body, and a conclusion . What you include in each depends on the objective of your literature review.

The introduction should clearly establish the focus and purpose of the literature review.

Depending on the length of your literature review, you might want to divide the body into subsections. You can use a subheading for each theme, time period, or methodological approach.

As you write, you can follow these tips:

• Summarize and synthesize: give an overview of the main points of each source and combine them into a coherent whole
• Analyze and interpret: don’t just paraphrase other researchers — add your own interpretations where possible, discussing the significance of findings in relation to the literature as a whole
• Critically evaluate: mention the strengths and weaknesses of your sources
• Write in well-structured paragraphs: use transition words and topic sentences to draw connections, comparisons and contrasts

In the conclusion, you should summarize the key findings you have taken from the literature and emphasize their significance.

When you’ve finished writing and revising your literature review, don’t forget to proofread thoroughly before submitting. Not a language expert? Check out Scribbr’s professional proofreading services !

This article has been adapted into lecture slides that you can use to teach your students about writing a literature review.

Scribbr slides are free to use, customize, and distribute for educational purposes.

Open Google Slides Download PowerPoint

If you want to know more about the research process , methodology , research bias , or statistics , make sure to check out some of our other articles with explanations and examples.

• Sampling methods
• Simple random sampling
• Stratified sampling
• Cluster sampling
• Likert scales
• Reproducibility

 Statistics

• Null hypothesis
• Statistical power
• Probability distribution
• Effect size
• Poisson distribution

Research bias

• Optimism bias
• Cognitive bias
• Implicit bias
• Hawthorne effect
• Anchoring bias
• Explicit bias

A literature review is a survey of scholarly sources (such as books, journal articles, and theses) related to a specific topic or research question .

It is often written as part of a thesis, dissertation , or research paper , in order to situate your work in relation to existing knowledge.

There are several reasons to conduct a literature review at the beginning of a research project:

• To familiarize yourself with the current state of knowledge on your topic
• To ensure that you’re not just repeating what others have already done
• To identify gaps in knowledge and unresolved problems that your research can address
• To develop your theoretical framework and methodology
• To provide an overview of the key findings and debates on the topic

Writing the literature review shows your reader how your work relates to existing research and what new insights it will contribute.

The literature review usually comes near the beginning of your thesis or dissertation . After the introduction , it grounds your research in a scholarly field and leads directly to your theoretical framework or methodology .

A literature review is a survey of credible sources on a topic, often used in dissertations , theses, and research papers . Literature reviews give an overview of knowledge on a subject, helping you identify relevant theories and methods, as well as gaps in existing research. Literature reviews are set up similarly to other  academic texts , with an introduction , a main body, and a conclusion .

An  annotated bibliography is a list of  source references that has a short description (called an annotation ) for each of the sources. It is often assigned as part of the research process for a  paper .  

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the “Cite this Scribbr article” button to automatically add the citation to our free Citation Generator.

McCombes, S. (2023, September 11). How to Write a Literature Review | Guide, Examples, & Templates. Scribbr. Retrieved August 26, 2024, from https://www.scribbr.com/dissertation/literature-review/

Is this article helpful?

Shona McCombes

Other students also liked, what is a theoretical framework | guide to organizing, what is a research methodology | steps & tips, how to write a research proposal | examples & templates, "i thought ai proofreading was useless but..".

I've been using Scribbr for years now and I know it's a service that won't disappoint. It does a good job spotting mistakes”

15 Literature Review Examples

Chris Drew (PhD)

Dr. Chris Drew is the founder of the Helpful Professor. He holds a PhD in education and has published over 20 articles in scholarly journals. He is the former editor of the Journal of Learning Development in Higher Education. [Image Descriptor: Photo of Chris]

Learn about our Editorial Process

Literature reviews are a necessary step in a research process and often required when writing your research proposal . They involve gathering, analyzing, and evaluating existing knowledge about a topic in order to find gaps in the literature where future studies will be needed.

Ideally, once you have completed your literature review, you will be able to identify how your research project can build upon and extend existing knowledge in your area of study.

Generally, for my undergraduate research students, I recommend a narrative review, where themes can be generated in order for the students to develop sufficient understanding of the topic so they can build upon the themes using unique methods or novel research questions.

If you’re in the process of writing a literature review, I have developed a literature review template for you to use – it’s a huge time-saver and walks you through how to write a literature review step-by-step:

Get your time-saving templates here to write your own literature review.

Literature Review Examples

For the following types of literature review, I present an explanation and overview of the type, followed by links to some real-life literature reviews on the topics.

1. Narrative Review Examples

Also known as a traditional literature review, the narrative review provides a broad overview of the studies done on a particular topic.

It often includes both qualitative and quantitative studies and may cover a wide range of years.

The narrative review’s purpose is to identify commonalities, gaps, and contradictions in the literature .

I recommend to my students that they should gather their studies together, take notes on each study, then try to group them by themes that form the basis for the review (see my step-by-step instructions at the end of the article).

Example Study

Title: Communication in healthcare: a narrative review of the literature and practical recommendations

Citation: Vermeir, P., Vandijck, D., Degroote, S., Peleman, R., Verhaeghe, R., Mortier, E., … & Vogelaers, D. (2015). Communication in healthcare: a narrative review of the literature and practical recommendations. International journal of clinical practice , 69 (11), 1257-1267.

Source: https://onlinelibrary.wiley.com/doi/pdf/10.1111/ijcp.12686  

Overview: This narrative review analyzed themes emerging from 69 articles about communication in healthcare contexts. Five key themes were found in the literature: poor communication can lead to various negative outcomes, discontinuity of care, compromise of patient safety, patient dissatisfaction, and inefficient use of resources. After presenting the key themes, the authors recommend that practitioners need to approach healthcare communication in a more structured way, such as by ensuring there is a clear understanding of who is in charge of ensuring effective communication in clinical settings.

Other Examples

• Burnout in United States Healthcare Professionals: A Narrative Review (Reith, 2018) – read here
• Examining the Presence, Consequences, and Reduction of Implicit Bias in Health Care: A Narrative Review (Zestcott, Blair & Stone, 2016) – read here
• A Narrative Review of School-Based Physical Activity for Enhancing Cognition and Learning (Mavilidi et al., 2018) – read here
• A narrative review on burnout experienced by medical students and residents (Dyrbye & Shanafelt, 2015) – read here

2. Systematic Review Examples

This type of literature review is more structured and rigorous than a narrative review. It involves a detailed and comprehensive plan and search strategy derived from a set of specified research questions.

The key way you’d know a systematic review compared to a narrative review is in the methodology: the systematic review will likely have a very clear criteria for how the studies were collected, and clear explanations of exclusion/inclusion criteria. 

The goal is to gather the maximum amount of valid literature on the topic, filter out invalid or low-quality reviews, and minimize bias. Ideally, this will provide more reliable findings, leading to higher-quality conclusions and recommendations for further research.

You may note from the examples below that the ‘method’ sections in systematic reviews tend to be much more explicit, often noting rigid inclusion/exclusion criteria and exact keywords used in searches.

Title: The importance of food naturalness for consumers: Results of a systematic review  

Citation: Roman, S., Sánchez-Siles, L. M., & Siegrist, M. (2017). The importance of food naturalness for consumers: Results of a systematic review. Trends in food science & technology , 67 , 44-57.

Source: https://www.sciencedirect.com/science/article/pii/S092422441730122X  

Overview: This systematic review included 72 studies of food naturalness to explore trends in the literature about its importance for consumers. Keywords used in the data search included: food, naturalness, natural content, and natural ingredients. Studies were included if they examined consumers’ preference for food naturalness and contained empirical data. The authors found that the literature lacks clarity about how naturalness is defined and measured, but also found that food consumption is significantly influenced by perceived naturalness of goods.

• A systematic review of research on online teaching and learning from 2009 to 2018 (Martin, Sun & Westine, 2020) – read here
• Where Is Current Research on Blockchain Technology? (Yli-Huumo et al., 2016) – read here
• Universities—industry collaboration: A systematic review (Ankrah & Al-Tabbaa, 2015) – read here
• Internet of Things Applications: A Systematic Review (Asghari, Rahmani & Javadi, 2019) – read here

3. Meta-analysis

This is a type of systematic review that uses statistical methods to combine and summarize the results of several studies.

Due to its robust methodology, a meta-analysis is often considered the ‘gold standard’ of secondary research , as it provides a more precise estimate of a treatment effect than any individual study contributing to the pooled analysis.

Furthermore, by aggregating data from a range of studies, a meta-analysis can identify patterns, disagreements, or other interesting relationships that may have been hidden in individual studies.

This helps to enhance the generalizability of findings, making the conclusions drawn from a meta-analysis particularly powerful and informative for policy and practice.

Title: Cholesterol and Alzheimer’s Disease Risk: A Meta-Meta-Analysis

Citation: Sáiz-Vazquez, O., Puente-Martínez, A., Ubillos-Landa, S., Pacheco-Bonrostro, J., & Santabárbara, J. (2020). Cholesterol and Alzheimer’s disease risk: a meta-meta-analysis. Brain sciences, 10(6), 386.

Source: https://doi.org/10.3390/brainsci10060386  

O verview: This study examines the relationship between cholesterol and Alzheimer’s disease (AD). Researchers conducted a systematic search of meta-analyses and reviewed several databases, collecting 100 primary studies and five meta-analyses to analyze the connection between cholesterol and Alzheimer’s disease. They find that the literature compellingly demonstrates that low-density lipoprotein cholesterol (LDL-C) levels significantly influence the development of Alzheimer’s disease.

• The power of feedback revisited: A meta-analysis of educational feedback research (Wisniewski, Zierer & Hattie, 2020) – read here
• How Much Does Education Improve Intelligence? A Meta-Analysis (Ritchie & Tucker-Drob, 2018) – read here
• A meta-analysis of factors related to recycling (Geiger et al., 2019) – read here
• Stress management interventions for police officers and recruits (Patterson, Chung & Swan, 2014) – read here

Other Types of Reviews

• Scoping Review: This type of review is used to map the key concepts underpinning a research area and the main sources and types of evidence available. It can be undertaken as stand-alone projects in their own right, or as a precursor to a systematic review.
• Rapid Review: This type of review accelerates the systematic review process in order to produce information in a timely manner. This is achieved by simplifying or omitting stages of the systematic review process.
• Integrative Review: This review method is more inclusive than others, allowing for the simultaneous inclusion of experimental and non-experimental research. The goal is to more comprehensively understand a particular phenomenon.
• Critical Review: This is similar to a narrative review but requires a robust understanding of both the subject and the existing literature. In a critical review, the reviewer not only summarizes the existing literature, but also evaluates its strengths and weaknesses. This is common in the social sciences and humanities .
• State-of-the-Art Review: This considers the current level of advancement in a field or topic and makes recommendations for future research directions. This type of review is common in technological and scientific fields but can be applied to any discipline.

How to Write a Narrative Review (Tips for Undergrad Students)

Most undergraduate students conducting a capstone research project will be writing narrative reviews. Below is a five-step process for conducting a simple review of the literature for your project.

• Search for Relevant Literature: Use scholarly databases related to your field of study, provided by your university library, along with appropriate search terms to identify key scholarly articles that have been published on your topic.
• Evaluate and Select Sources: Filter the source list by selecting studies that are directly relevant and of sufficient quality, considering factors like credibility , objectivity, accuracy, and validity.
• Analyze and Synthesize: Review each source and summarize the main arguments  in one paragraph (or more, for postgrad). Keep these summaries in a table.
• Identify Themes: With all studies summarized, group studies that share common themes, such as studies that have similar findings or methodologies.
• Write the Review: Write your review based upon the themes or subtopics you have identified. Give a thorough overview of each theme, integrating source data, and conclude with a summary of the current state of knowledge then suggestions for future research based upon your evaluation of what is lacking in the literature.

Literature reviews don’t have to be as scary as they seem. Yes, they are difficult and require a strong degree of comprehension of academic studies. But it can be feasibly done through following a structured approach to data collection and analysis. With my undergraduate research students (who tend to conduct small-scale qualitative studies ), I encourage them to conduct a narrative literature review whereby they can identify key themes in the literature. Within each theme, students can critique key studies and their strengths and limitations , in order to get a lay of the land and come to a point where they can identify ways to contribute new insights to the existing academic conversation on their topic.

Ankrah, S., & Omar, A. T. (2015). Universities–industry collaboration: A systematic review. Scandinavian Journal of Management, 31(3), 387-408.

Asghari, P., Rahmani, A. M., & Javadi, H. H. S. (2019). Internet of Things applications: A systematic review. Computer Networks , 148 , 241-261.

Dyrbye, L., & Shanafelt, T. (2016). A narrative review on burnout experienced by medical students and residents. Medical education , 50 (1), 132-149.

Geiger, J. L., Steg, L., Van Der Werff, E., & Ünal, A. B. (2019). A meta-analysis of factors related to recycling. Journal of environmental psychology , 64 , 78-97.

Martin, F., Sun, T., & Westine, C. D. (2020). A systematic review of research on online teaching and learning from 2009 to 2018. Computers & education , 159 , 104009.

Mavilidi, M. F., Ruiter, M., Schmidt, M., Okely, A. D., Loyens, S., Chandler, P., & Paas, F. (2018). A narrative review of school-based physical activity for enhancing cognition and learning: The importance of relevancy and integration. Frontiers in psychology , 2079.

Patterson, G. T., Chung, I. W., & Swan, P. W. (2014). Stress management interventions for police officers and recruits: A meta-analysis. Journal of experimental criminology , 10 , 487-513.

Reith, T. P. (2018). Burnout in United States healthcare professionals: a narrative review. Cureus , 10 (12).

Ritchie, S. J., & Tucker-Drob, E. M. (2018). How much does education improve intelligence? A meta-analysis. Psychological science , 29 (8), 1358-1369.

Roman, S., Sánchez-Siles, L. M., & Siegrist, M. (2017). The importance of food naturalness for consumers: Results of a systematic review. Trends in food science & technology , 67 , 44-57.

Sáiz-Vazquez, O., Puente-Martínez, A., Ubillos-Landa, S., Pacheco-Bonrostro, J., & Santabárbara, J. (2020). Cholesterol and Alzheimer’s disease risk: a meta-meta-analysis. Brain sciences, 10(6), 386.

Vermeir, P., Vandijck, D., Degroote, S., Peleman, R., Verhaeghe, R., Mortier, E., … & Vogelaers, D. (2015). Communication in healthcare: a narrative review of the literature and practical recommendations. International journal of clinical practice , 69 (11), 1257-1267.

Wisniewski, B., Zierer, K., & Hattie, J. (2020). The power of feedback revisited: A meta-analysis of educational feedback research. Frontiers in Psychology , 10 , 3087.

Yli-Huumo, J., Ko, D., Choi, S., Park, S., & Smolander, K. (2016). Where is current research on blockchain technology?—a systematic review. PloS one , 11 (10), e0163477.

Zestcott, C. A., Blair, I. V., & Stone, J. (2016). Examining the presence, consequences, and reduction of implicit bias in health care: a narrative review. Group Processes & Intergroup Relations , 19 (4), 528-542

• Chris Drew (PhD) https://helpfulprofessor.com/author/chris-drew-phd-2/ 21 Montessori Homeschool Setups
• Chris Drew (PhD) https://helpfulprofessor.com/author/chris-drew-phd-2/ 101 Hidden Talents Examples
• Chris Drew (PhD) https://helpfulprofessor.com/author/chris-drew-phd-2/ 15 Green Flags in a Relationship
• Chris Drew (PhD) https://helpfulprofessor.com/author/chris-drew-phd-2/ 15 Signs you're Burnt Out, Not Lazy

Leave a Comment Cancel Reply

Your email address will not be published. Required fields are marked *

What is a Literature Review? How to Write It (with Examples)

A literature review is a critical analysis and synthesis of existing research on a particular topic. It provides an overview of the current state of knowledge, identifies gaps, and highlights key findings in the literature. 1 The purpose of a literature review is to situate your own research within the context of existing scholarship, demonstrating your understanding of the topic and showing how your work contributes to the ongoing conversation in the field. Learning how to write a literature review is a critical tool for successful research. Your ability to summarize and synthesize prior research pertaining to a certain topic demonstrates your grasp on the topic of study, and assists in the learning process. 

Table of Contents

• What is the purpose of literature review? 
• a. Habitat Loss and Species Extinction: 
• b. Range Shifts and Phenological Changes: 
• c. Ocean Acidification and Coral Reefs: 
• d. Adaptive Strategies and Conservation Efforts: 

How to write a good literature review 

• Choose a Topic and Define the Research Question: 
• Decide on the Scope of Your Review: 
• Select Databases for Searches: 
• Conduct Searches and Keep Track: 
• Review the Literature: 
• Organize and Write Your Literature Review: 
• How to write a literature review faster with Paperpal? 
• Frequently asked questions 

What is a literature review?

A well-conducted literature review demonstrates the researcher’s familiarity with the existing literature, establishes the context for their own research, and contributes to scholarly conversations on the topic. One of the purposes of a literature review is also to help researchers avoid duplicating previous work and ensure that their research is informed by and builds upon the existing body of knowledge.

What is the purpose of literature review?

A literature review serves several important purposes within academic and research contexts. Here are some key objectives and functions of a literature review: 2  

1. Contextualizing the Research Problem: The literature review provides a background and context for the research problem under investigation. It helps to situate the study within the existing body of knowledge. 

2. Identifying Gaps in Knowledge: By identifying gaps, contradictions, or areas requiring further research, the researcher can shape the research question and justify the significance of the study. This is crucial for ensuring that the new research contributes something novel to the field. 

Find academic papers related to your research topic faster. Try Research on Paperpal  

3. Understanding Theoretical and Conceptual Frameworks: Literature reviews help researchers gain an understanding of the theoretical and conceptual frameworks used in previous studies. This aids in the development of a theoretical framework for the current research. 

4. Providing Methodological Insights: Another purpose of literature reviews is that it allows researchers to learn about the methodologies employed in previous studies. This can help in choosing appropriate research methods for the current study and avoiding pitfalls that others may have encountered. 

5. Establishing Credibility: A well-conducted literature review demonstrates the researcher’s familiarity with existing scholarship, establishing their credibility and expertise in the field. It also helps in building a solid foundation for the new research. 

6. Informing Hypotheses or Research Questions: The literature review guides the formulation of hypotheses or research questions by highlighting relevant findings and areas of uncertainty in existing literature. 

Literature review example

Let’s delve deeper with a literature review example: Let’s say your literature review is about the impact of climate change on biodiversity. You might format your literature review into sections such as the effects of climate change on habitat loss and species extinction, phenological changes, and marine biodiversity. Each section would then summarize and analyze relevant studies in those areas, highlighting key findings and identifying gaps in the research. The review would conclude by emphasizing the need for further research on specific aspects of the relationship between climate change and biodiversity. The following literature review template provides a glimpse into the recommended literature review structure and content, demonstrating how research findings are organized around specific themes within a broader topic. 

Literature Review on Climate Change Impacts on Biodiversity:

Climate change is a global phenomenon with far-reaching consequences, including significant impacts on biodiversity. This literature review synthesizes key findings from various studies: 

a. Habitat Loss and Species Extinction:

Climate change-induced alterations in temperature and precipitation patterns contribute to habitat loss, affecting numerous species (Thomas et al., 2004). The review discusses how these changes increase the risk of extinction, particularly for species with specific habitat requirements. 

b. Range Shifts and Phenological Changes:

Observations of range shifts and changes in the timing of biological events (phenology) are documented in response to changing climatic conditions (Parmesan & Yohe, 2003). These shifts affect ecosystems and may lead to mismatches between species and their resources. 

c. Ocean Acidification and Coral Reefs:

The review explores the impact of climate change on marine biodiversity, emphasizing ocean acidification’s threat to coral reefs (Hoegh-Guldberg et al., 2007). Changes in pH levels negatively affect coral calcification, disrupting the delicate balance of marine ecosystems. 

d. Adaptive Strategies and Conservation Efforts:

Recognizing the urgency of the situation, the literature review discusses various adaptive strategies adopted by species and conservation efforts aimed at mitigating the impacts of climate change on biodiversity (Hannah et al., 2007). It emphasizes the importance of interdisciplinary approaches for effective conservation planning. 

Strengthen your literature review with factual insights. Try Research on Paperpal for free!    

Writing a literature review involves summarizing and synthesizing existing research on a particular topic. A good literature review format should include the following elements. 

Introduction: The introduction sets the stage for your literature review, providing context and introducing the main focus of your review. 

• Opening Statement: Begin with a general statement about the broader topic and its significance in the field. 
• Scope and Purpose: Clearly define the scope of your literature review. Explain the specific research question or objective you aim to address. 
• Organizational Framework: Briefly outline the structure of your literature review, indicating how you will categorize and discuss the existing research. 
• Significance of the Study: Highlight why your literature review is important and how it contributes to the understanding of the chosen topic. 
• Thesis Statement: Conclude the introduction with a concise thesis statement that outlines the main argument or perspective you will develop in the body of the literature review. 

Body: The body of the literature review is where you provide a comprehensive analysis of existing literature, grouping studies based on themes, methodologies, or other relevant criteria. 

• Organize by Theme or Concept: Group studies that share common themes, concepts, or methodologies. Discuss each theme or concept in detail, summarizing key findings and identifying gaps or areas of disagreement. 
• Critical Analysis: Evaluate the strengths and weaknesses of each study. Discuss the methodologies used, the quality of evidence, and the overall contribution of each work to the understanding of the topic. 
• Synthesis of Findings: Synthesize the information from different studies to highlight trends, patterns, or areas of consensus in the literature. 
• Identification of Gaps: Discuss any gaps or limitations in the existing research and explain how your review contributes to filling these gaps. 
• Transition between Sections: Provide smooth transitions between different themes or concepts to maintain the flow of your literature review. 

Write and Cite as you go with Paperpal Research. Start now for free.   

Conclusion: The conclusion of your literature review should summarize the main findings, highlight the contributions of the review, and suggest avenues for future research. 

• Summary of Key Findings: Recap the main findings from the literature and restate how they contribute to your research question or objective. 
• Contributions to the Field: Discuss the overall contribution of your literature review to the existing knowledge in the field. 
• Implications and Applications: Explore the practical implications of the findings and suggest how they might impact future research or practice. 
• Recommendations for Future Research: Identify areas that require further investigation and propose potential directions for future research in the field. 
• Final Thoughts: Conclude with a final reflection on the importance of your literature review and its relevance to the broader academic community. 

Conducting a literature review

Conducting a literature review is an essential step in research that involves reviewing and analyzing existing literature on a specific topic. It’s important to know how to do a literature review effectively, so here are the steps to follow: 1  

Choose a Topic and Define the Research Question:

• Select a topic that is relevant to your field of study. 
• Clearly define your research question or objective. Determine what specific aspect of the topic do you want to explore? 

Decide on the Scope of Your Review:

• Determine the timeframe for your literature review. Are you focusing on recent developments, or do you want a historical overview? 
• Consider the geographical scope. Is your review global, or are you focusing on a specific region? 
• Define the inclusion and exclusion criteria. What types of sources will you include? Are there specific types of studies or publications you will exclude? 

Select Databases for Searches:

• Identify relevant databases for your field. Examples include PubMed, IEEE Xplore, Scopus, Web of Science, and Google Scholar. 
• Consider searching in library catalogs, institutional repositories, and specialized databases related to your topic. 

Conduct Searches and Keep Track:

• Develop a systematic search strategy using keywords, Boolean operators (AND, OR, NOT), and other search techniques. 
• Record and document your search strategy for transparency and replicability. 
• Keep track of the articles, including publication details, abstracts, and links. Use citation management tools like EndNote, Zotero, or Mendeley to organize your references. 

Review the Literature:

• Evaluate the relevance and quality of each source. Consider the methodology, sample size, and results of studies. 
• Organize the literature by themes or key concepts. Identify patterns, trends, and gaps in the existing research. 
• Summarize key findings and arguments from each source. Compare and contrast different perspectives. 
• Identify areas where there is a consensus in the literature and where there are conflicting opinions. 
• Provide critical analysis and synthesis of the literature. What are the strengths and weaknesses of existing research? 

Organize and Write Your Literature Review:

• Literature review outline should be based on themes, chronological order, or methodological approaches. 
• Write a clear and coherent narrative that synthesizes the information gathered. 
• Use proper citations for each source and ensure consistency in your citation style (APA, MLA, Chicago, etc.). 
• Conclude your literature review by summarizing key findings, identifying gaps, and suggesting areas for future research. 

Whether you’re exploring a new research field or finding new angles to develop an existing topic, sifting through hundreds of papers can take more time than you have to spare. But what if you could find science-backed insights with verified citations in seconds? That’s the power of Paperpal’s new Research feature!  

How to write a literature review faster with Paperpal?

Paperpal, an AI writing assistant, integrates powerful academic search capabilities within its writing platform. With the Research feature, you get 100% factual insights, with citations backed by 250M+ verified research articles, directly within your writing interface with the option to save relevant references in your Citation Library. By eliminating the need to switch tabs to find answers to all your research questions, Paperpal saves time and helps you stay focused on your writing.   

Here’s how to use the Research feature:  

• Ask a question: Get started with a new document on paperpal.com. Click on the “Research” feature and type your question in plain English. Paperpal will scour over 250 million research articles, including conference papers and preprints, to provide you with accurate insights and citations. 
• Review and Save: Paperpal summarizes the information, while citing sources and listing relevant reads. You can quickly scan the results to identify relevant references and save these directly to your built-in citations library for later access. 
• Cite with Confidence: Paperpal makes it easy to incorporate relevant citations and references into your writing, ensuring your arguments are well-supported by credible sources. This translates to a polished, well-researched literature review. 

The literature review sample and detailed advice on writing and conducting a review will help you produce a well-structured report. But remember that a good literature review is an ongoing process, and it may be necessary to revisit and update it as your research progresses. By combining effortless research with an easy citation process, Paperpal Research streamlines the literature review process and empowers you to write faster and with more confidence. Try Paperpal Research now and see for yourself.  

Frequently asked questions

A literature review is a critical and comprehensive analysis of existing literature (published and unpublished works) on a specific topic or research question and provides a synthesis of the current state of knowledge in a particular field. A well-conducted literature review is crucial for researchers to build upon existing knowledge, avoid duplication of efforts, and contribute to the advancement of their field. It also helps researchers situate their work within a broader context and facilitates the development of a sound theoretical and conceptual framework for their studies.

Literature review is a crucial component of research writing, providing a solid background for a research paper’s investigation. The aim is to keep professionals up to date by providing an understanding of ongoing developments within a specific field, including research methods, and experimental techniques used in that field, and present that knowledge in the form of a written report. Also, the depth and breadth of the literature review emphasizes the credibility of the scholar in his or her field.  

Before writing a literature review, it’s essential to undertake several preparatory steps to ensure that your review is well-researched, organized, and focused. This includes choosing a topic of general interest to you and doing exploratory research on that topic, writing an annotated bibliography, and noting major points, especially those that relate to the position you have taken on the topic. 

Literature reviews and academic research papers are essential components of scholarly work but serve different purposes within the academic realm. 3 A literature review aims to provide a foundation for understanding the current state of research on a particular topic, identify gaps or controversies, and lay the groundwork for future research. Therefore, it draws heavily from existing academic sources, including books, journal articles, and other scholarly publications. In contrast, an academic research paper aims to present new knowledge, contribute to the academic discourse, and advance the understanding of a specific research question. Therefore, it involves a mix of existing literature (in the introduction and literature review sections) and original data or findings obtained through research methods. 

Literature reviews are essential components of academic and research papers, and various strategies can be employed to conduct them effectively. If you want to know how to write a literature review for a research paper, here are four common approaches that are often used by researchers.  Chronological Review: This strategy involves organizing the literature based on the chronological order of publication. It helps to trace the development of a topic over time, showing how ideas, theories, and research have evolved.  Thematic Review: Thematic reviews focus on identifying and analyzing themes or topics that cut across different studies. Instead of organizing the literature chronologically, it is grouped by key themes or concepts, allowing for a comprehensive exploration of various aspects of the topic.  Methodological Review: This strategy involves organizing the literature based on the research methods employed in different studies. It helps to highlight the strengths and weaknesses of various methodologies and allows the reader to evaluate the reliability and validity of the research findings.  Theoretical Review: A theoretical review examines the literature based on the theoretical frameworks used in different studies. This approach helps to identify the key theories that have been applied to the topic and assess their contributions to the understanding of the subject.  It’s important to note that these strategies are not mutually exclusive, and a literature review may combine elements of more than one approach. The choice of strategy depends on the research question, the nature of the literature available, and the goals of the review. Additionally, other strategies, such as integrative reviews or systematic reviews, may be employed depending on the specific requirements of the research.

The literature review format can vary depending on the specific publication guidelines. However, there are some common elements and structures that are often followed. Here is a general guideline for the format of a literature review:  Introduction:   Provide an overview of the topic.  Define the scope and purpose of the literature review.  State the research question or objective.  Body:   Organize the literature by themes, concepts, or chronology.  Critically analyze and evaluate each source.  Discuss the strengths and weaknesses of the studies.  Highlight any methodological limitations or biases.  Identify patterns, connections, or contradictions in the existing research.  Conclusion:   Summarize the key points discussed in the literature review.  Highlight the research gap.  Address the research question or objective stated in the introduction.  Highlight the contributions of the review and suggest directions for future research.

Both annotated bibliographies and literature reviews involve the examination of scholarly sources. While annotated bibliographies focus on individual sources with brief annotations, literature reviews provide a more in-depth, integrated, and comprehensive analysis of existing literature on a specific topic. The key differences are as follows: 

References 

• Denney, A. S., & Tewksbury, R. (2013). How to write a literature review.  Journal of criminal justice education ,  24 (2), 218-234. 
• Pan, M. L. (2016).  Preparing literature reviews: Qualitative and quantitative approaches . Taylor & Francis. 
• Cantero, C. (2019). How to write a literature review.  San José State University Writing Center . 

Paperpal is an AI writing assistant that help academics write better, faster with real-time suggestions for in-depth language and grammar correction. Trained on millions of research manuscripts enhanced by professional academic editors, Paperpal delivers human precision at machine speed.  

Try it for free or upgrade to  Paperpal Prime , which unlocks unlimited access to premium features like academic translation, paraphrasing, contextual synonyms, consistency checks and more. It’s like always having a professional academic editor by your side! Go beyond limitations and experience the future of academic writing.  Get Paperpal Prime now at just US$19 a month!

Related Reads:

• Empirical Research: A Comprehensive Guide for Academics 
• How to Write a Scientific Paper in 10 Steps 
• How Long Should a Chapter Be?
• How to Use Paperpal to Generate Emails & Cover Letters?

6 Tips for Post-Doc Researchers to Take Their Career to the Next Level

Self-plagiarism in research: what it is and how to avoid it, you may also like, academic integrity vs academic dishonesty: types & examples, dissertation printing and binding | types & comparison , what is a dissertation preface definition and examples , the ai revolution: authors’ role in upholding academic..., the future of academia: how ai tools are..., how to write a research proposal: (with examples..., how to write your research paper in apa..., how to choose a dissertation topic, how to write a phd research proposal, how to write an academic paragraph (step-by-step guide).

Literature Review

• Steps for Conducting a Lit Review
• Finding "The Literature"
• Organizing/Writing
• Sample Literature Reviews
• FAMU Writing Center

Sample Lit Reviews from Communication Arts

• Literature Review Sample 1
• Literature Review Sample 2
• Literature Review Sample 3
• << Previous: MLA Style
• Next: FAMU Writing Center >>
• Last Updated: Oct 20, 2022 11:24 AM
• URL: https://library.famu.edu/literaturereview

Literature Review Guide: Examples of Literature Reviews

• What is a Literature Review?
• How to start?
• Picking your research question and searching
• Search strategies and Databases
• How to organise the review
• Examples of Literature Reviews
• Library summary

All good quality journal articles will include a small Literature Review after the Introduction paragraph.  It may not be called a Literature Review but gives you an idea of how one is created in miniature.

Sample Literature Reviews as part of a articles or Theses

• Hackett, G and Melia, D . The hotel as the holiday/stay destination:trends and innovations. Presented at TRIC Conference, Belfast, Ireland- June 2012 and EuroCHRIE Conference

Links to sample Literature Reviews from other libraries

• Sample literature reviews from University of West Florida

Irish Theses

• Phillips, Martin (2015) European airline performance: a data envelopment analysis with extrapolations based on model outputs. Master of Business Studies thesis, Dublin City University.
• The customers’ perception of servicescape’s influence on their behaviours, in the food retail industry : Dublin Business School 2015
• Coughlan, Ray (2015) What was the role of leadership in the transformation of a failing Irish Insurance business. Masters thesis, Dublin, National College of Ireland.
• << Previous: How to organise the review
• Next: Library summary >>
• Last Updated: Aug 28, 2024 5:05 PM
• URL: https://ait.libguides.com/literaturereview

Reference management. Clean and simple.

What is a literature review? [with examples]

What is a literature review?

The purpose of a literature review, how to write a literature review, the format of a literature review, general formatting rules, the length of a literature review, literature review examples, frequently asked questions about literature reviews, related articles.

A literature review is an assessment of the sources in a chosen topic of research.

In a literature review, you’re expected to report on the existing scholarly conversation, without adding new contributions.

If you are currently writing one, you've come to the right place. In the following paragraphs, we will explain:

• the objective of a literature review
• how to write a literature review
• the basic format of a literature review

Tip: It’s not always mandatory to add a literature review in a paper. Theses and dissertations often include them, whereas research papers may not. Make sure to consult with your instructor for exact requirements.

The four main objectives of a literature review are:

• Studying the references of your research area
• Summarizing the main arguments
• Identifying current gaps, stances, and issues
• Presenting all of the above in a text

Ultimately, the main goal of a literature review is to provide the researcher with sufficient knowledge about the topic in question so that they can eventually make an intervention.

The format of a literature review is fairly standard. It includes an:

• introduction that briefly introduces the main topic
• body that includes the main discussion of the key arguments
• conclusion that highlights the gaps and issues of the literature

➡️ Take a look at our guide on how to write a literature review to learn more about how to structure a literature review.

First of all, a literature review should have its own labeled section. You should indicate clearly in the table of contents where the literature can be found, and you should label this section as “Literature Review.”

➡️ For more information on writing a thesis, visit our guide on how to structure a thesis .

There is no set amount of words for a literature review, so the length depends on the research. If you are working with a large amount of sources, it will be long. If your paper does not depend entirely on references, it will be short.

Take a look at these three theses featuring great literature reviews:

• School-Based Speech-Language Pathologist's Perceptions of Sensory Food Aversions in Children [ PDF , see page 20]
• Who's Writing What We Read: Authorship in Criminological Research [ PDF , see page 4]
• A Phenomenological Study of the Lived Experience of Online Instructors of Theological Reflection at Christian Institutions Accredited by the Association of Theological Schools [ PDF , see page 56]

Literature reviews are most commonly found in theses and dissertations. However, you find them in research papers as well.

There is no set amount of words for a literature review, so the length depends on the research. If you are working with a large amount of sources, then it will be long. If your paper does not depend entirely on references, then it will be short.

No. A literature review should have its own independent section. You should indicate clearly in the table of contents where the literature review can be found, and label this section as “Literature Review.”

The main goal of a literature review is to provide the researcher with sufficient knowledge about the topic in question so that they can eventually make an intervention.

WTO / Education / 39 Best Literature Review Examples (Guide with Samples)

39 Best Literature Review Examples (Guide with Samples)

A literature review is a compilation of current knowledge on a particular topic derived from the critical evaluation of different scholarly sources such as books, articles, and publications, which is then presented in an organized manner to relate to a specific research problem being investigated.

It highlights the methods, relevant theories, and gaps in existing research on a particular subject. It can be both a summary and synthesis of information on a specific topic. A summary reiterates key information from scholarly sources, while synthesis is a new interpretation or combination of new and old material. 

As a synthesis, it can outline the intellectual progression of knowledge in a particular field or topic, which might involve stating key debates throughout the advancement period.  

Literature Review Examples

Purpose of Literature Review

Literature reviews have different purposes in scholarly articles, research papers , and books, depending on the discipline at hand. First and foremost, reviews are generally meant to showcase the extensive research carried out by an author on a particular topic and their findings, which will form the foundation of the research. It then summarizes the information to show the author’s familiarity with the topic in question.

The review also demonstrates the relationship between the topic being investigated and other topics that were under consideration. Finally, it outlines the gaps in the previous works of other scholars, which create areas of research.

Literature reviews provide a new interpretation of previous scholarly publications and aim to resolve conflicting studies done in the past. In addition, identifying existing gaps in a particular research area illustrates the starting point of the research.

Literature Review vs. Academic Research Paper

A research paper presents new ideas, arguments, and approaches toward a particular topic. The conclusions of a research paper will be based on the analysis and interpretation of raw data collected by the author and an original study. On the other hand, a literature review is based on the findings of other publications. Thus, the review highlights the author’s understanding of a topic based on the previously conducted research. It is part of a research paper.

Where, When, and Why

The need for a literature review in a publication will vary from one situation to the other and the field/discipline of research. These two factors determine what is expected from the lit review. For example, a scientific review will be more analytical on the methods and results of previous research. In contrast, a philosophical review will be more argumentative, highlighting the discrepancies and correspondences between scholars.

It can either be part of a publication or a stand-alone document. As part of a research publication, it is often placed after the introduction to the topic outlining knowledge about a particular topic and critical sources that formed the foundation of the research. As an individual document, it is prepared by students as part of course study to aid the students in familiarizing themselves with different topics in their field of study.

Lit reviews also guide students to help them synthesize theoretical methodologies and frameworks to adopt in academic research . As a publication, literature reviews are used to document existing information about a topic for readers (other scholars) to go through for whatever reasons they may have. Published studies are essentially helpful to new scholars getting into any field of research.

Types of Literature Review

Before looking into how to write a literature review, it is vital to understand the different types. The type will usually depend on the objective approach of the author.

Common types are:  

Argumentative review

An argumentative review is adopted when the research paper or publication is meant to take a contrarian viewpoint on a particular subject. The review analyses an existing argument, philosophical problem, assumption, or conclusion outlined in different studies with an objective to either support or oppose the argument. 

Integrative review

An integrative review integrates secondary data to develop new perspectives and frameworks on a topic. This is more prevalent in research that does not involve primary data. In addition, integrative reviews are more familiar with social sciences.       

Historical review

Historical reviews are used when scholars or authors place a particular idea, concept, theory, or research in a historical context. It examines the idea, theory, or issue from the first time it was discussed and outlines its evolution throughout a given period.  

Methodological review

Methodological reviews look at how a specific theory, concept, results, or findings were developed. Therefore, methodological reviews will analyze the different methods used by different scholars to arrive at conclusions or knowledge about the topic being investigated.

Some of the methods scholars use in different disciplines to obtain information are interviewing, sampling, practical experiments/data collection, research approaches, critical thinking, social experiments, etc.

Methodological reviews are hence used to discuss tested methods of research and ethics that a researcher should be aware of before undertaking their investigations.  

Systematic review

A systematic review is a more detailed and comprehensive review compared to other types of lit reviews. It highlights any existing research evidence associated with a clearly defined research problem or question. The evidence is collected, analyzed, and reported in a summarized but detailed manner. Systematic reviews are popularly presented as a cause-and-effect structure.

Theoretical review

A theoretical review delves into the different theories regarding a particular issue, challenge, concept, or theory. It identifies their inadequacy in explaining the issue or concept at hand. The review then identifies the relationships between the identified theories, and the degree of research done and poses novel hypotheses to be investigated.

Organization of a Literature Review

How an author organizes a literature review will depend on what they aim to achieve. As a consequence, there are multiple ways of organizing it which are discussed below:

Chronological 

A chronological format outlines knowledge on a particular topic based on when the scholarly source of information was published. Starting with the earliest followed up to the most recent chronological order. This format should be used if there is a clear chronological order in the development of the information; therefore, it will not be applicable in some cases. Instead, key turning points, patterns, and events that impacted the direction of the knowledge should be outlined.  

By publication

It can be organized in the scholarly publications reviewed by the author, scholar, or student. The by-publication format should only improve the review and facilitate what the author aims to accomplish. 

Scholars or students can adopt a dominant trend in research, such as history, developmental stages, steps involved in a process, etc.

Methodological

A methodological format is based on the methods used by the researcher. Thus, the order of contents in the lit review will depend on the method they will use to carry out their research, knowledge obtained from the first method appears first, and the rest of the information follows in the same order according to the methods used by the author.  

Literature reviews organized in a thematic format revolve around the subject being investigated in no order. It is, therefore, ordinarily up to the researcher or author to determine how they intend to outline the information. A thematic format will crossover from one period and publication to another, but can sometimes incorporate a chronological order.

Theoretical

Literature reviews organized in a theoretical format have their contents organized in an abstract framework established by the author to discuss different concepts, theories, and concepts and how they relate to the research at hand.

Additional sections

Depending on the objective, other sections do not fit under conventional lit review formats that one may need to add. Below are some of the sections that authors or students can include in the lit review:

• Current situation: The review can have information about the current state of things regarding the topic at hand to facilitate further understanding.
• History: Researchers can summarize the subject under investigation, literature, or concept if the review is not already in chronological format.
• Selection methods: Lit reviews are known to outline the methods or criteria used in selecting the way to present information and scholarly sources referenced in the review.
• Standards: it can also include the standards used in choosing the format to present information in the review and the scholarly literature used in the research.
• Further questions for research: The review can include questions emanating from the review and how the researcher will further explore their research to address the queries raised.

Literature Review Samples

Considerations Before Writing a Literature Review

Preparation is essential when it comes to writing. The objective should be to come up with a review that satisfactorily explores the topic being discussed. The following considerations are steps towards that if incorporated into the writing process:

Authors should seek clarification from mentors or supervisors before commencing the writing process. First, determine what is expected from the lit review. The type and number of sources to be used, the assignment (summarize, synthesize, or critique), and the type of information provided should be clear.

Find models

You should review literature from other authors in the same discipline and evaluate how those authors presented their lit reviews. Previous lit reviews can be used as guides that point authors in the right direction when writing their lit reviews.

Narrow your topic

It is always advantageous to narrow down the research topic to a specific area of research; that way, the number of sources can also be reduced. Even though conducting research will usually involve extensive research on all available materials about a particular topic, having a well-defined topic simplifies the task at hand.

Current sources

Determine if the research project or discipline ought to be based on the most recent findings or information. It is common for knowledge to become obsolete, especially in disciplines where discoveries and new inventions are made fast. If the lit review should be based on current knowledge, limit the sources to the most recent literature. Some disciplines will typically have a limit on how old the sources should be.  

How to Write a Literature Review (Expert Guide)

Once all pre-writing considerations have been taken into account, it is time to write the document. At this point, you should already be aware of what you wish to accomplish with the literature review, and the steps to writing an exemplary lit review are mentioned below:

Problem formulation

First and foremost, clearly define the topic (research area) to be investigated. For students, this will sometimes be given as an assignment. However, the research could be an academic project, which means that the author has to come up with the problem and define it themselves.

Search for relevant studies

Once the problem is clearly expressed, you should search for studies related to the topic, concept, theory, or idea and questions surrounding the topic. Most stand-alone lit reviews will generally attempt to answer a more concentrated question. On the internet, literature can be searched using keywords related to the research area. In addition to keywords, include vital variables such as synonyms and associated terms. The inclusion of Boolean operators and, or not, is also used to narrow down results to more specific publications.

Familiar sources for publications are:

• Google Scholar
• Library catalogue
• Econ lit (economics)
• Project Muse (humanities and social sciences)
• Inspec (physics, engineering, and computer science )
• Medline (life sciences and biomedicine)

Before selecting relevant studies, go through their abstract and determine if they fit the scope needed in the investigation. Use a list to note down any chosen works. Select landmark sources in the discipline.

Evaluation of sources/data

The next step is the evaluation stage . Evaluation involves a lot of reading. Evaluation can be done in two stages; overall skimming and thorough reading. During the second stage of this step, be critical, ask questions, and take many notes.

Some of the questions authors or researchers should ask themselves are:

• What is the author’s objective? What problem, concept, or theory are they putting across?
• What are the main concepts?
• What are the methodologies used by the author to arrive at the results and conclusions?
• What are the strengths and weaknesses of the results and conclusions?

Use credible sources. Most cited sources are preferred as they indicate their influence in the field. Also, keep track of the citations to be later incorporated.

Identify themes, debates, and gaps

While reading the sources, identify key patterns, themes, debates/arguments, and gaps in each literature. These elements help tie the literature to the topic under investigation. Look for consistent patterns, themes, questions, challenges, methods, and inconsistencies in the same. Consistencies present critical information for consideration, while inconsistencies present opportunities for research areas.

Outline the structure

Formatting is part and parcel of a well-written work. Selecting the structure should start by creating an outline with all the information that will go into the lit review, then consider the different types of structures and select the most suitable. Next, take the basic structure of the introduction, body, and conclusion into consideration and start work from there. 

Analysis and interpretation 

Lastly, perform an in-depth analysis and interpretation of the information obtained from the scholarly research and put it into writing. The summarized, synthesized, and critically evaluated information is then written down in well-structured paragraphs that follow the chosen structure. Transition words are used to draw comparisons, connections, and contrasts.

Format 

Ordinarily, a literature review will have three key components: introduction, body, and conclusion. These components should appear in the document in the following order:

Introduction

An introduction should inform the reader which topic is being studied. It gives the reader an overall idea of the purpose and focus of the document. The introduction lets the reader know beforehand the key things that will be highlighted in the document. Therefore, the introduction should be brief and precise.

The next item is the body, where the primary purpose of the lit review is fulfilled. The body should take critical information from all the sources used and comprehensively present them. This is where the author reports the extensive analysis and interpretation results that they gathered from all the sources they reviewed. The body should be categorized into themes, ideas, and concepts within the main topic.

Lastly, a summary of what the lit review entails should be provided as a conclusion. The critical points obtained from examining the sources should be written down and linked to the primary subject of the review. Key points are those that have the most outstanding contribution to the research.

Studies used should be screened based on provenance (author’s credentials or credibility), methodology, objectivity, persuasiveness, and value related to the topic at hand.

Guidelines for Writing a Literature Review

To improve the delivery of information, there are certain elements that authors can incorporate. They are:

Use evidence

The lit review’s findings, interpretations, and general contents should be based on actual evidence or credible literature. Using citations is evidence of authentic information.

Be selective

There will always be a lot of information available from the reviewed sources. Authors should therefore be selective and discuss the key points that focus on the topic. Not all information must be included in the review.  

Word-for-word quotes are acceptable . This is even more so if a critical point or author-specific terminology or knowledge cannot be paraphrased. Quotes should, however, be used sparingly.

Summarize and synthesize

The information obtained from the sources should be summarized, and the author should use it to synthesize new arguments, concepts, or ideas related to their research.

Keep your voice

The literature review should reflect the author’s voice as it is a review of other people’s works. This can be done by starting and ending the paragraphs with an original voice, ideas, and wordings.

Use caution while paraphrasing

Any paraphrased information should be conveyed accurately and in the author’s words. A citation must always be done, even when paraphrasing has been done.

Proofread before submitting or publishing. Go through the document a few times and make the necessary changes. The review should be within the applicable guidelines. Check for language and any other errors and edit accordingly.

Do’s and Don’ts for a Literature Review 

Every researcher wants to introduce their readers to a particular topic in an informative and engaging manner. Below are tips that can be used to this effect.

The following things should be opted by the researcher when writing a lit review:

• Find a focus: Authors should take a direction, idea, concept, or argument and stick to it. The information conveyed should then be made to align with the chosen point of focus. Thus, the review is not simply a list of analyzed sources, but a detailed summary of how different sources have a focal point (intertwined).
• Well-chosen sources: The quality of the information will, to a great extent, be determined by the quality of sources used. Therefore, take time to select suitable sources and more value will be added to the review.
• Create an annotated bibliography: Creating an annotated bibliography is recommended as one reads their sources. The bibliography keeps track of sources and takes notes. This information can be used when writing the final lit review.
• Synthesize research: Information obtained from the relevant studies should be combined to come up with new or original ideas. You should present a new domain based on previous sources’ knowledge, not just restating the information.
• Argumentative approach: Well-written literature reviews will often argue to support an author’s stance on a particular topic. The author can choose to address how the author’s work is filling a particular gap or support one of the scholar’s arguments and perception towards a particular topic. However, this argumentative approach will not work in all situations; it is usually discipline-specific. 
• Convey it to the reader: It should let the reader know the document’s main idea, concept, or argument. This can be done by including a simple statement that compels the reader to think precisely and know what to expect.
• Break out your disciplinary box: The research will often be multi-disciplinary. Literature reviews should then collect interdisciplinary information from multiple sources as they add novel dynamics to the topic under investigation. It should be noted that this does not imply that the researcher should substitute the literature from the topic’s discipline with that from other disciplines. This is usually an improvement strategy that adds substance to the review.
• Look for repeated patterns: Be attentive to pick out repeated ideas, findings, and concepts from different scholars as they will often illustrate agreed research dead-end or a scholarly conclusion.
• Don’t just review for content: When reviewing the literature, examine the content and other writing and presentation techniques. Look out for unique ways information has been presented, methods used, consistent citations, and non-textual elements such as graphs, and figures used to present information. In addition, the researcher identifies theories used to predict, explain, or understand phenomena within the discipline.
• Search Web of Science and Google Scholar: Conduct citation tracking about the leading scholars already identified in the search process. Scholars cited by multiple scholars outside the principal discipline will generally indicate that there are no new publications on the topic.

The following don’ts should be avoided:

• Do not select studies that are not directly related to the topic being investigated.
• Avoid rushing when identifying and selecting sources to use to research the problem.
• Avoid the use of secondary analytical sources. Instead, opt to use sources with primary research studies or data. Secondary analytical sources will often cite primary analytical sources; research should refer to them instead.
• Do not accept other scholarly findings, theories, or interpretations without critically examining and critiquing them.
• Researchers should not outline the search procedures used to identify scholarly sources for reviewing purposes.
• Avoid including isolated statistical findings without illustrating how they were arrived at using chi-squared or meta-analytic methods.
• Do not review studies that only validate the assumptions, stances, and concepts of your thesis; consider contradicting works with alternative and conflicting stances.

Frequently Asked Questions

It is written by researchers, authors, and students who must study literature to gather knowledge on a particular topic they are interested in.

It should be placed right after the introduction of the dissertation. It places the research in a scholarly context by summarizing existing knowledge on the particular topic.

Researchers and authors are not limited in terms of how many sources they can review. Students will usually have a given number of sources to review as an assignment. However, the number of sources referenced in a lit review will vary from one topic or discipline to the other. Some topics have a vast catalog of available sources, while others have minimal sources, especially emerging issues. It is, however, advised that each key point discussed should have at least 2-3 references/sources. For example, a 10-page lit review will have an average of 30 references.

About This Article

Was this helpful?

Great! Tell us more about your experience

Not up to par help us fix it, keep reading.

Education , Guides

20+ free printable graph paper templates – pdf.

Charts , Education

35 printable homeschool schedule templates [free].

Graduation Speech Ideas (18 Outline Examples)

Education , Receipts

14 free school fee receipt templates (word | pdf), thank you for your feedback.

Your Voice, Our Progress. Your feedback matters a lot to us.

The Sheridan Libraries

• Write a Literature Review
• Sheridan Libraries
• Evaluate This link opens in a new window

What Will You Do Differently?

Please help your librarians by filling out this two-minute survey of today's class session..

Professor, this one's for you .

Introduction

Literature reviews take time. here is some general information to know before you start.  .

•  VIDEO -- This video is a great overview of the entire process.  (2020; North Carolina State University Libraries) --The transcript is included --This is for everyone; ignore the mention of "graduate students" --9.5 minutes, and every second is important  
• OVERVIEW -- Read this page from Purdue's OWL. It's not long, and gives some tips to fill in what you just learned from the video.  
• NOT A RESEARCH ARTICLE -- A literature review follows a different style, format, and structure from a research article.  

• Next: Evaluate >>
• Last Updated: Jul 30, 2024 1:42 PM
• URL: https://guides.library.jhu.edu/lit-review

Purdue Online Writing Lab Purdue OWL® College of Liberal Arts

Writing a Literature Review

Welcome to the Purdue OWL

This page is brought to you by the OWL at Purdue University. When printing this page, you must include the entire legal notice.

Copyright ©1995-2018 by The Writing Lab & The OWL at Purdue and Purdue University. All rights reserved. This material may not be published, reproduced, broadcast, rewritten, or redistributed without permission. Use of this site constitutes acceptance of our terms and conditions of fair use.

A literature review is a document or section of a document that collects key sources on a topic and discusses those sources in conversation with each other (also called synthesis ). The lit review is an important genre in many disciplines, not just literature (i.e., the study of works of literature such as novels and plays). When we say “literature review” or refer to “the literature,” we are talking about the research ( scholarship ) in a given field. You will often see the terms “the research,” “the scholarship,” and “the literature” used mostly interchangeably.

Where, when, and why would I write a lit review?

There are a number of different situations where you might write a literature review, each with slightly different expectations; different disciplines, too, have field-specific expectations for what a literature review is and does. For instance, in the humanities, authors might include more overt argumentation and interpretation of source material in their literature reviews, whereas in the sciences, authors are more likely to report study designs and results in their literature reviews; these differences reflect these disciplines’ purposes and conventions in scholarship. You should always look at examples from your own discipline and talk to professors or mentors in your field to be sure you understand your discipline’s conventions, for literature reviews as well as for any other genre.

A literature review can be a part of a research paper or scholarly article, usually falling after the introduction and before the research methods sections. In these cases, the lit review just needs to cover scholarship that is important to the issue you are writing about; sometimes it will also cover key sources that informed your research methodology.

Lit reviews can also be standalone pieces, either as assignments in a class or as publications. In a class, a lit review may be assigned to help students familiarize themselves with a topic and with scholarship in their field, get an idea of the other researchers working on the topic they’re interested in, find gaps in existing research in order to propose new projects, and/or develop a theoretical framework and methodology for later research. As a publication, a lit review usually is meant to help make other scholars’ lives easier by collecting and summarizing, synthesizing, and analyzing existing research on a topic. This can be especially helpful for students or scholars getting into a new research area, or for directing an entire community of scholars toward questions that have not yet been answered.

What are the parts of a lit review?

Most lit reviews use a basic introduction-body-conclusion structure; if your lit review is part of a larger paper, the introduction and conclusion pieces may be just a few sentences while you focus most of your attention on the body. If your lit review is a standalone piece, the introduction and conclusion take up more space and give you a place to discuss your goals, research methods, and conclusions separately from where you discuss the literature itself.

Introduction:

• An introductory paragraph that explains what your working topic and thesis is
• A forecast of key topics or texts that will appear in the review
• Potentially, a description of how you found sources and how you analyzed them for inclusion and discussion in the review (more often found in published, standalone literature reviews than in lit review sections in an article or research paper)
• Summarize and synthesize: Give an overview of the main points of each source and combine them into a coherent whole
• Analyze and interpret: Don’t just paraphrase other researchers – add your own interpretations where possible, discussing the significance of findings in relation to the literature as a whole
• Critically Evaluate: Mention the strengths and weaknesses of your sources
• Write in well-structured paragraphs: Use transition words and topic sentence to draw connections, comparisons, and contrasts.

Conclusion:

• Summarize the key findings you have taken from the literature and emphasize their significance
• Connect it back to your primary research question

How should I organize my lit review?

Lit reviews can take many different organizational patterns depending on what you are trying to accomplish with the review. Here are some examples:

• Chronological : The simplest approach is to trace the development of the topic over time, which helps familiarize the audience with the topic (for instance if you are introducing something that is not commonly known in your field). If you choose this strategy, be careful to avoid simply listing and summarizing sources in order. Try to analyze the patterns, turning points, and key debates that have shaped the direction of the field. Give your interpretation of how and why certain developments occurred (as mentioned previously, this may not be appropriate in your discipline — check with a teacher or mentor if you’re unsure).
• Thematic : If you have found some recurring central themes that you will continue working with throughout your piece, you can organize your literature review into subsections that address different aspects of the topic. For example, if you are reviewing literature about women and religion, key themes can include the role of women in churches and the religious attitude towards women.
• Qualitative versus quantitative research
• Empirical versus theoretical scholarship
• Divide the research by sociological, historical, or cultural sources
• Theoretical : In many humanities articles, the literature review is the foundation for the theoretical framework. You can use it to discuss various theories, models, and definitions of key concepts. You can argue for the relevance of a specific theoretical approach or combine various theorical concepts to create a framework for your research.

What are some strategies or tips I can use while writing my lit review?

Any lit review is only as good as the research it discusses; make sure your sources are well-chosen and your research is thorough. Don’t be afraid to do more research if you discover a new thread as you’re writing. More info on the research process is available in our "Conducting Research" resources .

As you’re doing your research, create an annotated bibliography ( see our page on the this type of document ). Much of the information used in an annotated bibliography can be used also in a literature review, so you’ll be not only partially drafting your lit review as you research, but also developing your sense of the larger conversation going on among scholars, professionals, and any other stakeholders in your topic.

Usually you will need to synthesize research rather than just summarizing it. This means drawing connections between sources to create a picture of the scholarly conversation on a topic over time. Many student writers struggle to synthesize because they feel they don’t have anything to add to the scholars they are citing; here are some strategies to help you:

• It often helps to remember that the point of these kinds of syntheses is to show your readers how you understand your research, to help them read the rest of your paper.
• Writing teachers often say synthesis is like hosting a dinner party: imagine all your sources are together in a room, discussing your topic. What are they saying to each other?
• Look at the in-text citations in each paragraph. Are you citing just one source for each paragraph? This usually indicates summary only. When you have multiple sources cited in a paragraph, you are more likely to be synthesizing them (not always, but often
• Read more about synthesis here.

The most interesting literature reviews are often written as arguments (again, as mentioned at the beginning of the page, this is discipline-specific and doesn’t work for all situations). Often, the literature review is where you can establish your research as filling a particular gap or as relevant in a particular way. You have some chance to do this in your introduction in an article, but the literature review section gives a more extended opportunity to establish the conversation in the way you would like your readers to see it. You can choose the intellectual lineage you would like to be part of and whose definitions matter most to your thinking (mostly humanities-specific, but this goes for sciences as well). In addressing these points, you argue for your place in the conversation, which tends to make the lit review more compelling than a simple reporting of other sources.

APA Literature Review

Ai generator.

The realm of academia thrives on knowledge expansion, and a crucial element in this quest is the literature review. Whether it be delving into an extensive body of research, analyzing a book or article, or comprehending a research paper format , the literature review serves as a cornerstone for scholarly pursuits. In this article, we explore the intricacies of an APA literature review, providing a step-by-step guide on how to craft one effectively. Let us embark on this enlightening journey, acquainting ourselves with the vital aspects of citation, in-text citation, and the construction of a reference list. Along the way, we will answer three frequently asked questions to further enhance your understanding. So, let’s dive in!

1. Literature Review Template

• Google Docs

2. APA Literature Review

Size: 24 KB

3. Instruction for APA Style Literature Review

Size: 181 KB

4. APA Style Literature Review

Size: 616 KB

5. Sections of APA Literature Review

Size: 26 KB

6. APA Paper Literature Review

Size: 799 KB

7. APA Style Literature Review Example

Size: 120 KB

8. Types of APA Paper Literature Review

Size: 411 KB

9. Sociology APA Literature Review

10. APA Writing Style and Language Literature Review

Size: 269 KB

11. APA Literature Review in Psychology

Size: 454 KB

12. APA Literature Review Format

13. APA Style Literature Review Guidelines

Size: 134 KB

14. APA Annotated Bibliography Literature Review

Size: 55 KB

15. APA Literature Review Guidelines

Size: 107 KB

16. APA Literature Review Citation

Size: 30 KB

17. APA Literature Review Action Research Proposal

Size: 15 KB

18. APA 6th Edition Literature Review

Size: 734 KB

19. APA Writing Literature Review

Size: 110 KB

20. APA Contextual Literature Review

Size: 605 KB

What is an APA Literature Review?

An APA literature review encapsulates a systematic examination and synthesis of scholarly sources relevant to a specific research topic. It serves to provide a comprehensive overview of the existing knowledge, identify gaps in research, and present a theoretical foundation for further investigation. Distinct from a book review or an article review that focuses on analyzing a single publication, a literature review involves an in-depth exploration of a broad range of sources. By adhering to the guidelines set forth by the American Psychological Association (APA), this review ensures clarity, consistency, and credibility throughout the process.

How to Write an APA Literature Review

Embarking on the journey of crafting an APA literature review requires careful planning and meticulous execution. By following these steps, you can streamline your writing process and ensure a cohesive and comprehensive review.

Select a Topic:

Begin by choosing a research topic that aligns with your area of interest or academic requirements. This topic should be broad enough to provide an adequate range of relevant sources but specific enough to maintain focus.

Gather Relevant Literature:

Conduct a thorough search of scholarly databases, libraries, and academic journals to collect a diverse array of sources that contribute to your topic. Evaluate the quality and relevance of each source to ensure credibility and significance.

Read and Analyze:

Engage critically with each selected source, comprehending the key arguments, methodologies, and findings presented. Take diligent notes and identify common themes or gaps in the existing literature to guide the structure of your review.

Organize Your Thoughts:

Create an outline to organize your literature review effectively. Arrange the sources thematically or chronologically to present a logical flow of information. Introduce each section with an informative heading to guide the reader.

Compose the Review:

Begin writing your literature review by providing an engaging introduction that highlights the importance of the topic and presents the scope of your review. Subsequently, present the findings from each source, critically evaluating the methodologies, results, and implications. Use appropriate in-text citations to acknowledge the authors and support your claims.

Conclude with Insight:

Wrap up your literature review with a well-crafted conclusion that summarizes the main findings, identifies research gaps, and suggests avenues for future investigation. Reinforce the significance of your review and its contribution to the existing body of knowledge.

What is the difference between a literature review and a book review?

A literature review examines a range of scholarly sources on a specific topic, while a book review focuses on analyzing a single publication, typically for the purpose of providing a critique or evaluation.

Do I need to include all the sources I find in my literature review?

No, it is crucial to evaluate the quality and relevance of each source. Include sources that contribute significantly to your research topic and present diverse perspectives.

How can I format the reference list in APA style?

The APA style requires a specific format for the reference list. To ensure accuracy, you can check out 9+ reference list examples here , which demonstrate how to cite different types of sources in APA format.

The journey of crafting an APA literature review demands meticulous research, critical analysis, and skillful presentation. By immersing yourself in the vast sea of literature, navigating the intricacies of citation and in-text citation , and adhering to the guidelines set forth by APA, you can construct a compelling review that contributes to the scholarly discourse. So, let your words breathe life into the existing body of knowledge, igniting the curiosity of readers and propelling the pursuit of wisdom forward. Happy reviewing!

Text prompt

• Instructive
• Professional

10 Examples of Public speaking

20 Examples of Gas lighting

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• CAREER FEATURE
• 04 December 2020
• Correction 09 December 2020

How to write a superb literature review

Andy Tay is a freelance writer based in Singapore.

You can also search for this author in PubMed   Google Scholar

Credit: Getty

Literature reviews are important resources for scientists. They provide historical context for a field while offering opinions on its future trajectory. Creating them can provide inspiration for one’s own research, as well as some practice in writing. But few scientists are trained in how to write a review — or in what constitutes an excellent one. Even picking the appropriate software to use can be an involved decision (see ‘Tools and techniques’). So Nature asked editors and working scientists with well-cited reviews for their tips.

WENTING ZHAO: Be focused and avoid jargon

Assistant professor of chemical and biomedical engineering, Nanyang Technological University, Singapore.

When I was a research student, review writing improved my understanding of the history of my field. I also learnt about unmet challenges in the field that triggered ideas.

For example, while writing my first review 1 as a PhD student, I was frustrated by how poorly we understood how cells actively sense, interact with and adapt to nanoparticles used in drug delivery. This experience motivated me to study how the surface properties of nanoparticles can be modified to enhance biological sensing. When I transitioned to my postdoctoral research, this question led me to discover the role of cell-membrane curvature, which led to publications and my current research focus. I wouldn’t have started in this area without writing that review.

Collection: Careers toolkit

A common problem for students writing their first reviews is being overly ambitious. When I wrote mine, I imagined producing a comprehensive summary of every single type of nanomaterial used in biological applications. It ended up becoming a colossal piece of work, with too many papers discussed and without a clear way to categorize them. We published the work in the end, but decided to limit the discussion strictly to nanoparticles for biological sensing, rather than covering how different nanomaterials are used in biology.

My advice to students is to accept that a review is unlike a textbook: it should offer a more focused discussion, and it’s OK to skip some topics so that you do not distract your readers. Students should also consider editorial deadlines, especially for invited reviews: make sure that the review’s scope is not so extensive that it delays the writing.

A good review should also avoid jargon and explain the basic concepts for someone who is new to the field. Although I trained as an engineer, I’m interested in biology, and my research is about developing nanomaterials to manipulate proteins at the cell membrane and how this can affect ageing and cancer. As an ‘outsider’, the reviews that I find most useful for these biological topics are those that speak to me in accessible scientific language.

Bozhi Tian likes to get a variety of perspectives into a review. Credit: Aleksander Prominski

BOZHI TIAN: Have a process and develop your style

Associate professor of chemistry, University of Chicago, Illinois.

In my lab, we start by asking: what is the purpose of this review? My reasons for writing one can include the chance to contribute insights to the scientific community and identify opportunities for my research. I also see review writing as a way to train early-career researchers in soft skills such as project management and leadership. This is especially true for lead authors, because they will learn to work with their co-authors to integrate the various sections into a piece with smooth transitions and no overlaps.

After we have identified the need and purpose of a review article, I will form a team from the researchers in my lab. I try to include students with different areas of expertise, because it is useful to get a variety of perspectives. For example, in the review ‘An atlas of nano-enabled neural interfaces’ 2 , we had authors with backgrounds in biophysics, neuroengineering, neurobiology and materials sciences focusing on different sections of the review.

After this, I will discuss an outline with my team. We go through multiple iterations to make sure that we have scanned the literature sufficiently and do not repeat discussions that have appeared in other reviews. It is also important that the outline is not decided by me alone: students often have fresh ideas that they can bring to the table. Once this is done, we proceed with the writing.

I often remind my students to imagine themselves as ‘artists of science’ and encourage them to develop how they write and present information. Adding more words isn’t always the best way: for example, I enjoy using tables to summarize research progress and suggest future research trajectories. I’ve also considered including short videos in our review papers to highlight key aspects of the work. I think this can increase readership and accessibility because these videos can be easily shared on social-media platforms.

ANKITA ANIRBAN: Timeliness and figures make a huge difference

Editor, Nature Reviews Physics .

One of my roles as a journal editor is to evaluate proposals for reviews. The best proposals are timely and clearly explain why readers should pay attention to the proposed topic.

It is not enough for a review to be a summary of the latest growth in the literature: the most interesting reviews instead provide a discussion about disagreements in the field.

Careers Collection: Publishing

Scientists often centre the story of their primary research papers around their figures — but when it comes to reviews, figures often take a secondary role. In my opinion, review figures are more important than most people think. One of my favourite review-style articles 3 presents a plot bringing together data from multiple research papers (many of which directly contradict each other). This is then used to identify broad trends and suggest underlying mechanisms that could explain all of the different conclusions.

An important role of a review article is to introduce researchers to a field. For this, schematic figures can be useful to illustrate the science being discussed, in much the same way as the first slide of a talk should. That is why, at Nature Reviews, we have in-house illustrators to assist authors. However, simplicity is key, and even without support from professional illustrators, researchers can still make use of many free drawing tools to enhance the value of their review figures.

Yoojin Choi recommends that researchers be open to critiques when writing reviews. Credit: Yoojin Choi

YOOJIN CHOI: Stay updated and be open to suggestions

Research assistant professor, Korea Advanced Institute of Science and Technology, Daejeon.

I started writing the review ‘Biosynthesis of inorganic nanomaterials using microbial cells and bacteriophages’ 4 as a PhD student in 2018. It took me one year to write the first draft because I was working on the review alongside my PhD research and mostly on my own, with support from my adviser. It took a further year to complete the processes of peer review, revision and publication. During this time, many new papers and even competing reviews were published. To provide the most up-to-date and original review, I had to stay abreast of the literature. In my case, I made use of Google Scholar, which I set to send me daily updates of relevant literature based on key words.

Through my review-writing process, I also learnt to be more open to critiques to enhance the value and increase the readership of my work. Initially, my review was focused only on using microbial cells such as bacteria to produce nanomaterials, which was the subject of my PhD research. Bacteria such as these are known as biofactories: that is, organisms that produce biological material which can be modified to produce useful materials, such as magnetic nanoparticles for drug-delivery purposes.

Synchronized editing: the future of collaborative writing

However, when the first peer-review report came back, all three reviewers suggested expanding the review to cover another type of biofactory: bacteriophages. These are essentially viruses that infect bacteria, and they can also produce nanomaterials.

The feedback eventually led me to include a discussion of the differences between the various biofactories (bacteriophages, bacteria, fungi and microalgae) and their advantages and disadvantages. This turned out to be a great addition because it made the review more comprehensive.

Writing the review also led me to an idea about using nanomaterial-modified microorganisms to produce chemicals, which I’m still researching now.

PAULA MARTIN-GONZALEZ: Make good use of technology

PhD student, University of Cambridge, UK.

Just before the coronavirus lockdown, my PhD adviser and I decided to write a literature review discussing the integration of medical imaging with genomics to improve ovarian cancer management.

As I was researching the review, I noticed a trend in which some papers were consistently being cited by many other papers in the field. It was clear to me that those papers must be important, but as a new member of the field of integrated cancer biology, it was difficult to immediately find and read all of these ‘seminal papers’.

That was when I decided to code a small application to make my literature research more efficient. Using my code, users can enter a query, such as ‘ovarian cancer, computer tomography, radiomics’, and the application searches for all relevant literature archived in databases such as PubMed that feature these key words.

The code then identifies the relevant papers and creates a citation graph of all the references cited in the results of the search. The software highlights papers that have many citation relationships with other papers in the search, and could therefore be called seminal papers.

My code has substantially improved how I organize papers and has informed me of key publications and discoveries in my research field: something that would have taken more time and experience in the field otherwise. After I shared my code on GitHub, I received feedback that it can be daunting for researchers who are not used to coding. Consequently, I am hoping to build a more user-friendly interface in a form of a web page, akin to PubMed or Google Scholar, where users can simply input their queries to generate citation graphs.

Tools and techniques

Most reference managers on the market offer similar capabilities when it comes to providing a Microsoft Word plug-in and producing different citation styles. But depending on your working preferences, some might be more suitable than others.

Reference managers

Here is a comparison of the more popular collaborative writing tools, but there are other options, including Fidus Writer, Manuscript.io, Authorea and Stencila.

Collaborative writing tools

*Markdown and LaTex are code-based formatting languages favoured by physicists, mathematicians and computer scientists who code on a regular basis, and less popular in other disciplines such as biology and chemistry.

doi: https://doi.org/10.1038/d41586-020-03422-x

Interviews have been edited for length and clarity.

Updates & Corrections

Correction 09 December 2020 : An earlier version of the tables in this article included some incorrect details about the programs Zotero, Endnote and Manubot. These have now been corrected.

Hsing, I.-M., Xu, Y. & Zhao, W. Electroanalysis 19 , 755–768 (2007).

Article   Google Scholar  

Ledesma, H. A. et al. Nature Nanotechnol. 14 , 645–657 (2019).

Article   PubMed   Google Scholar  

Brahlek, M., Koirala, N., Bansal, N. & Oh, S. Solid State Commun. 215–216 , 54–62 (2015).

Choi, Y. & Lee, S. Y. Nature Rev. Chem . https://doi.org/10.1038/s41570-020-00221-w (2020).

Download references

Related Articles

• Research management

Tales of a migratory marine biologist

Career Feature 28 AUG 24

Nail your tech-industry interviews with these six techniques

Career Column 28 AUG 24

How to harness AI’s potential in research — responsibly and ethically

Career Feature 23 AUG 24

Binning out-of-date chemicals? Somebody think about the carbon!

Correspondence 27 AUG 24

No more hunting for replication studies: crowdsourced database makes them easy to find

Nature Index 27 AUG 24

Partners in drug discovery: how to collaborate with non-governmental organizations

Exclusive: the papers that most heavily cite retracted studies

News 28 AUG 24

Chain retraction: how to stop bad science propagating through the literature

Comment 28 AUG 24

Supervisory Bioinformatics Specialist CTG Program Head

The National Library of Medicine (NLM) is a global leader in biomedical informatics and computational health data science and the world’s largest b...

Bethesda, Maryland (US)

National Library of Medicine, National Center for Biotechnology Information

Post Doctoral Research Scientist

Post-Doctoral Research Scientist Position in Human Transplant Immunology at the Columbia Center for Translational Immunology in New York, NY

New York City, New York (US)

Columbia Center for Translational Immunoogy

Postdoctoral Associate- Neuromodulation and Computational Psychiatry

Houston, Texas (US)

Baylor College of Medicine (BCM)

Postdoctoral Fellow

Modeling Autism Spectrum Disorders using genetically modified human stem cell-derived brain organoids and mouse models.

Weill Cornell Medical College

Scientific Visualization Developer

APPLICATION CLOSING DATE: September 29th, 2024   About the institute Human Technopole (HT) is an interdisciplinary life science research institute,...

Human Technopole

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• PLoS Comput Biol
• v.9(7); 2013 Jul

Ten Simple Rules for Writing a Literature Review

Marco pautasso.

1 Centre for Functional and Evolutionary Ecology (CEFE), CNRS, Montpellier, France

2 Centre for Biodiversity Synthesis and Analysis (CESAB), FRB, Aix-en-Provence, France

Literature reviews are in great demand in most scientific fields. Their need stems from the ever-increasing output of scientific publications [1] . For example, compared to 1991, in 2008 three, eight, and forty times more papers were indexed in Web of Science on malaria, obesity, and biodiversity, respectively [2] . Given such mountains of papers, scientists cannot be expected to examine in detail every single new paper relevant to their interests [3] . Thus, it is both advantageous and necessary to rely on regular summaries of the recent literature. Although recognition for scientists mainly comes from primary research, timely literature reviews can lead to new synthetic insights and are often widely read [4] . For such summaries to be useful, however, they need to be compiled in a professional way [5] .

When starting from scratch, reviewing the literature can require a titanic amount of work. That is why researchers who have spent their career working on a certain research issue are in a perfect position to review that literature. Some graduate schools are now offering courses in reviewing the literature, given that most research students start their project by producing an overview of what has already been done on their research issue [6] . However, it is likely that most scientists have not thought in detail about how to approach and carry out a literature review.

Reviewing the literature requires the ability to juggle multiple tasks, from finding and evaluating relevant material to synthesising information from various sources, from critical thinking to paraphrasing, evaluating, and citation skills [7] . In this contribution, I share ten simple rules I learned working on about 25 literature reviews as a PhD and postdoctoral student. Ideas and insights also come from discussions with coauthors and colleagues, as well as feedback from reviewers and editors.

Rule 1: Define a Topic and Audience

How to choose which topic to review? There are so many issues in contemporary science that you could spend a lifetime of attending conferences and reading the literature just pondering what to review. On the one hand, if you take several years to choose, several other people may have had the same idea in the meantime. On the other hand, only a well-considered topic is likely to lead to a brilliant literature review [8] . The topic must at least be:

• interesting to you (ideally, you should have come across a series of recent papers related to your line of work that call for a critical summary),
• an important aspect of the field (so that many readers will be interested in the review and there will be enough material to write it), and
• a well-defined issue (otherwise you could potentially include thousands of publications, which would make the review unhelpful).

Ideas for potential reviews may come from papers providing lists of key research questions to be answered [9] , but also from serendipitous moments during desultory reading and discussions. In addition to choosing your topic, you should also select a target audience. In many cases, the topic (e.g., web services in computational biology) will automatically define an audience (e.g., computational biologists), but that same topic may also be of interest to neighbouring fields (e.g., computer science, biology, etc.).

Rule 2: Search and Re-search the Literature

After having chosen your topic and audience, start by checking the literature and downloading relevant papers. Five pieces of advice here:

• keep track of the search items you use (so that your search can be replicated [10] ),
• keep a list of papers whose pdfs you cannot access immediately (so as to retrieve them later with alternative strategies),
• use a paper management system (e.g., Mendeley, Papers, Qiqqa, Sente),
• define early in the process some criteria for exclusion of irrelevant papers (these criteria can then be described in the review to help define its scope), and
• do not just look for research papers in the area you wish to review, but also seek previous reviews.

The chances are high that someone will already have published a literature review ( Figure 1 ), if not exactly on the issue you are planning to tackle, at least on a related topic. If there are already a few or several reviews of the literature on your issue, my advice is not to give up, but to carry on with your own literature review,

The bottom-right situation (many literature reviews but few research papers) is not just a theoretical situation; it applies, for example, to the study of the impacts of climate change on plant diseases, where there appear to be more literature reviews than research studies [33] .

• discussing in your review the approaches, limitations, and conclusions of past reviews,
• trying to find a new angle that has not been covered adequately in the previous reviews, and
• incorporating new material that has inevitably accumulated since their appearance.

When searching the literature for pertinent papers and reviews, the usual rules apply:

• be thorough,
• use different keywords and database sources (e.g., DBLP, Google Scholar, ISI Proceedings, JSTOR Search, Medline, Scopus, Web of Science), and
• look at who has cited past relevant papers and book chapters.

Rule 3: Take Notes While Reading

If you read the papers first, and only afterwards start writing the review, you will need a very good memory to remember who wrote what, and what your impressions and associations were while reading each single paper. My advice is, while reading, to start writing down interesting pieces of information, insights about how to organize the review, and thoughts on what to write. This way, by the time you have read the literature you selected, you will already have a rough draft of the review.

Of course, this draft will still need much rewriting, restructuring, and rethinking to obtain a text with a coherent argument [11] , but you will have avoided the danger posed by staring at a blank document. Be careful when taking notes to use quotation marks if you are provisionally copying verbatim from the literature. It is advisable then to reformulate such quotes with your own words in the final draft. It is important to be careful in noting the references already at this stage, so as to avoid misattributions. Using referencing software from the very beginning of your endeavour will save you time.

Rule 4: Choose the Type of Review You Wish to Write

After having taken notes while reading the literature, you will have a rough idea of the amount of material available for the review. This is probably a good time to decide whether to go for a mini- or a full review. Some journals are now favouring the publication of rather short reviews focusing on the last few years, with a limit on the number of words and citations. A mini-review is not necessarily a minor review: it may well attract more attention from busy readers, although it will inevitably simplify some issues and leave out some relevant material due to space limitations. A full review will have the advantage of more freedom to cover in detail the complexities of a particular scientific development, but may then be left in the pile of the very important papers “to be read” by readers with little time to spare for major monographs.

There is probably a continuum between mini- and full reviews. The same point applies to the dichotomy of descriptive vs. integrative reviews. While descriptive reviews focus on the methodology, findings, and interpretation of each reviewed study, integrative reviews attempt to find common ideas and concepts from the reviewed material [12] . A similar distinction exists between narrative and systematic reviews: while narrative reviews are qualitative, systematic reviews attempt to test a hypothesis based on the published evidence, which is gathered using a predefined protocol to reduce bias [13] , [14] . When systematic reviews analyse quantitative results in a quantitative way, they become meta-analyses. The choice between different review types will have to be made on a case-by-case basis, depending not just on the nature of the material found and the preferences of the target journal(s), but also on the time available to write the review and the number of coauthors [15] .

Rule 5: Keep the Review Focused, but Make It of Broad Interest

Whether your plan is to write a mini- or a full review, it is good advice to keep it focused 16 , 17 . Including material just for the sake of it can easily lead to reviews that are trying to do too many things at once. The need to keep a review focused can be problematic for interdisciplinary reviews, where the aim is to bridge the gap between fields [18] . If you are writing a review on, for example, how epidemiological approaches are used in modelling the spread of ideas, you may be inclined to include material from both parent fields, epidemiology and the study of cultural diffusion. This may be necessary to some extent, but in this case a focused review would only deal in detail with those studies at the interface between epidemiology and the spread of ideas.

While focus is an important feature of a successful review, this requirement has to be balanced with the need to make the review relevant to a broad audience. This square may be circled by discussing the wider implications of the reviewed topic for other disciplines.

Rule 6: Be Critical and Consistent

Reviewing the literature is not stamp collecting. A good review does not just summarize the literature, but discusses it critically, identifies methodological problems, and points out research gaps [19] . After having read a review of the literature, a reader should have a rough idea of:

• the major achievements in the reviewed field,
• the main areas of debate, and
• the outstanding research questions.

It is challenging to achieve a successful review on all these fronts. A solution can be to involve a set of complementary coauthors: some people are excellent at mapping what has been achieved, some others are very good at identifying dark clouds on the horizon, and some have instead a knack at predicting where solutions are going to come from. If your journal club has exactly this sort of team, then you should definitely write a review of the literature! In addition to critical thinking, a literature review needs consistency, for example in the choice of passive vs. active voice and present vs. past tense.

Rule 7: Find a Logical Structure

Like a well-baked cake, a good review has a number of telling features: it is worth the reader's time, timely, systematic, well written, focused, and critical. It also needs a good structure. With reviews, the usual subdivision of research papers into introduction, methods, results, and discussion does not work or is rarely used. However, a general introduction of the context and, toward the end, a recapitulation of the main points covered and take-home messages make sense also in the case of reviews. For systematic reviews, there is a trend towards including information about how the literature was searched (database, keywords, time limits) [20] .

How can you organize the flow of the main body of the review so that the reader will be drawn into and guided through it? It is generally helpful to draw a conceptual scheme of the review, e.g., with mind-mapping techniques. Such diagrams can help recognize a logical way to order and link the various sections of a review [21] . This is the case not just at the writing stage, but also for readers if the diagram is included in the review as a figure. A careful selection of diagrams and figures relevant to the reviewed topic can be very helpful to structure the text too [22] .

Rule 8: Make Use of Feedback

Reviews of the literature are normally peer-reviewed in the same way as research papers, and rightly so [23] . As a rule, incorporating feedback from reviewers greatly helps improve a review draft. Having read the review with a fresh mind, reviewers may spot inaccuracies, inconsistencies, and ambiguities that had not been noticed by the writers due to rereading the typescript too many times. It is however advisable to reread the draft one more time before submission, as a last-minute correction of typos, leaps, and muddled sentences may enable the reviewers to focus on providing advice on the content rather than the form.

Feedback is vital to writing a good review, and should be sought from a variety of colleagues, so as to obtain a diversity of views on the draft. This may lead in some cases to conflicting views on the merits of the paper, and on how to improve it, but such a situation is better than the absence of feedback. A diversity of feedback perspectives on a literature review can help identify where the consensus view stands in the landscape of the current scientific understanding of an issue [24] .

Rule 9: Include Your Own Relevant Research, but Be Objective

In many cases, reviewers of the literature will have published studies relevant to the review they are writing. This could create a conflict of interest: how can reviewers report objectively on their own work [25] ? Some scientists may be overly enthusiastic about what they have published, and thus risk giving too much importance to their own findings in the review. However, bias could also occur in the other direction: some scientists may be unduly dismissive of their own achievements, so that they will tend to downplay their contribution (if any) to a field when reviewing it.

In general, a review of the literature should neither be a public relations brochure nor an exercise in competitive self-denial. If a reviewer is up to the job of producing a well-organized and methodical review, which flows well and provides a service to the readership, then it should be possible to be objective in reviewing one's own relevant findings. In reviews written by multiple authors, this may be achieved by assigning the review of the results of a coauthor to different coauthors.

Rule 10: Be Up-to-Date, but Do Not Forget Older Studies

Given the progressive acceleration in the publication of scientific papers, today's reviews of the literature need awareness not just of the overall direction and achievements of a field of inquiry, but also of the latest studies, so as not to become out-of-date before they have been published. Ideally, a literature review should not identify as a major research gap an issue that has just been addressed in a series of papers in press (the same applies, of course, to older, overlooked studies (“sleeping beauties” [26] )). This implies that literature reviewers would do well to keep an eye on electronic lists of papers in press, given that it can take months before these appear in scientific databases. Some reviews declare that they have scanned the literature up to a certain point in time, but given that peer review can be a rather lengthy process, a full search for newly appeared literature at the revision stage may be worthwhile. Assessing the contribution of papers that have just appeared is particularly challenging, because there is little perspective with which to gauge their significance and impact on further research and society.

Inevitably, new papers on the reviewed topic (including independently written literature reviews) will appear from all quarters after the review has been published, so that there may soon be the need for an updated review. But this is the nature of science [27] – [32] . I wish everybody good luck with writing a review of the literature.

Acknowledgments

Many thanks to M. Barbosa, K. Dehnen-Schmutz, T. Döring, D. Fontaneto, M. Garbelotto, O. Holdenrieder, M. Jeger, D. Lonsdale, A. MacLeod, P. Mills, M. Moslonka-Lefebvre, G. Stancanelli, P. Weisberg, and X. Xu for insights and discussions, and to P. Bourne, T. Matoni, and D. Smith for helpful comments on a previous draft.

Funding Statement

This work was funded by the French Foundation for Research on Biodiversity (FRB) through its Centre for Synthesis and Analysis of Biodiversity data (CESAB), as part of the NETSEED research project. The funders had no role in the preparation of the manuscript.

How To Write An A-Grade Literature Review

3 straightforward steps (with examples) + free template.

By: Derek Jansen (MBA) | Expert Reviewed By: Dr. Eunice Rautenbach | October 2019

Quality research is about building onto the existing work of others , “standing on the shoulders of giants”, as Newton put it. The literature review chapter of your dissertation, thesis or research project is where you synthesise this prior work and lay the theoretical foundation for your own research.

Long story short, this chapter is a pretty big deal, which is why you want to make sure you get it right . In this post, I’ll show you exactly how to write a literature review in three straightforward steps, so you can conquer this vital chapter (the smart way).

Overview: The Literature Review Process

• Understanding the “ why “
• Finding the relevant literature
• Cataloguing and synthesising the information
• Outlining & writing up your literature review
• Example of a literature review

But first, the “why”…

Before we unpack how to write the literature review chapter, we’ve got to look at the why . To put it bluntly, if you don’t understand the function and purpose of the literature review process, there’s no way you can pull it off well. So, what exactly is the purpose of the literature review?

Well, there are (at least) four core functions:

• For you to gain an understanding (and demonstrate this understanding) of where the research is at currently, what the key arguments and disagreements are.
• For you to identify the gap(s) in the literature and then use this as justification for your own research topic.
• To help you build a conceptual framework for empirical testing (if applicable to your research topic).
• To inform your methodological choices and help you source tried and tested questionnaires (for interviews ) and measurement instruments (for surveys ).

Most students understand the first point but don’t give any thought to the rest. To get the most from the literature review process, you must keep all four points front of mind as you review the literature (more on this shortly), or you’ll land up with a wonky foundation.

Okay – with the why out the way, let’s move on to the how . As mentioned above, writing your literature review is a process, which I’ll break down into three steps:

• Finding the most suitable literature
• Understanding , distilling and organising the literature
• Planning and writing up your literature review chapter

Importantly, you must complete steps one and two before you start writing up your chapter. I know it’s very tempting, but don’t try to kill two birds with one stone and write as you read. You’ll invariably end up wasting huge amounts of time re-writing and re-shaping, or you’ll just land up with a disjointed, hard-to-digest mess . Instead, you need to read first and distil the information, then plan and execute the writing.

Step 1: Find the relevant literature

Naturally, the first step in the literature review journey is to hunt down the existing research that’s relevant to your topic. While you probably already have a decent base of this from your research proposal , you need to expand on this substantially in the dissertation or thesis itself.

Essentially, you need to be looking for any existing literature that potentially helps you answer your research question (or develop it, if that’s not yet pinned down). There are numerous ways to find relevant literature, but I’ll cover my top four tactics here. I’d suggest combining all four methods to ensure that nothing slips past you:

Method 1 – Google Scholar Scrubbing

Google’s academic search engine, Google Scholar , is a great starting point as it provides a good high-level view of the relevant journal articles for whatever keyword you throw at it. Most valuably, it tells you how many times each article has been cited, which gives you an idea of how credible (or at least, popular) it is. Some articles will be free to access, while others will require an account, which brings us to the next method.

Method 2 – University Database Scrounging

Generally, universities provide students with access to an online library, which provides access to many (but not all) of the major journals.

So, if you find an article using Google Scholar that requires paid access (which is quite likely), search for that article in your university’s database – if it’s listed there, you’ll have access. Note that, generally, the search engine capabilities of these databases are poor, so make sure you search for the exact article name, or you might not find it.

Method 3 – Journal Article Snowballing

At the end of every academic journal article, you’ll find a list of references. As with any academic writing, these references are the building blocks of the article, so if the article is relevant to your topic, there’s a good chance a portion of the referenced works will be too. Do a quick scan of the titles and see what seems relevant, then search for the relevant ones in your university’s database.

Method 4 – Dissertation Scavenging

Similar to Method 3 above, you can leverage other students’ dissertations. All you have to do is skim through literature review chapters of existing dissertations related to your topic and you’ll find a gold mine of potential literature. Usually, your university will provide you with access to previous students’ dissertations, but you can also find a much larger selection in the following databases:

• Open Access Theses & Dissertations
• Stanford SearchWorks

Keep in mind that dissertations and theses are not as academically sound as published, peer-reviewed journal articles (because they’re written by students, not professionals), so be sure to check the credibility of any sources you find using this method. You can do this by assessing the citation count of any given article in Google Scholar. If you need help with assessing the credibility of any article, or with finding relevant research in general, you can chat with one of our Research Specialists .

Alright – with a good base of literature firmly under your belt, it’s time to move onto the next step.

Need a helping hand?

Step 2: Log, catalogue and synthesise

Once you’ve built a little treasure trove of articles, it’s time to get reading and start digesting the information – what does it all mean?

While I present steps one and two (hunting and digesting) as sequential, in reality, it’s more of a back-and-forth tango – you’ll read a little , then have an idea, spot a new citation, or a new potential variable, and then go back to searching for articles. This is perfectly natural – through the reading process, your thoughts will develop , new avenues might crop up, and directional adjustments might arise. This is, after all, one of the main purposes of the literature review process (i.e. to familiarise yourself with the current state of research in your field).

As you’re working through your treasure chest, it’s essential that you simultaneously start organising the information. There are three aspects to this:

• Logging reference information
• Building an organised catalogue
• Distilling and synthesising the information

I’ll discuss each of these below:

2.1 – Log the reference information

As you read each article, you should add it to your reference management software. I usually recommend Mendeley for this purpose (see the Mendeley 101 video below), but you can use whichever software you’re comfortable with. Most importantly, make sure you load EVERY article you read into your reference manager, even if it doesn’t seem very relevant at the time.

2.2 – Build an organised catalogue

In the beginning, you might feel confident that you can remember who said what, where, and what their main arguments were. Trust me, you won’t. If you do a thorough review of the relevant literature (as you must!), you’re going to read many, many articles, and it’s simply impossible to remember who said what, when, and in what context . Also, without the bird’s eye view that a catalogue provides, you’ll miss connections between various articles, and have no view of how the research developed over time. Simply put, it’s essential to build your own catalogue of the literature.

I would suggest using Excel to build your catalogue, as it allows you to run filters, colour code and sort – all very useful when your list grows large (which it will). How you lay your spreadsheet out is up to you, but I’d suggest you have the following columns (at minimum):

• Author, date, title – Start with three columns containing this core information. This will make it easy for you to search for titles with certain words, order research by date, or group by author.
• Categories or keywords – You can either create multiple columns, one for each category/theme and then tick the relevant categories, or you can have one column with keywords.
• Key arguments/points – Use this column to succinctly convey the essence of the article, the key arguments and implications thereof for your research.
• Context – Note the socioeconomic context in which the research was undertaken. For example, US-based, respondents aged 25-35, lower- income, etc. This will be useful for making an argument about gaps in the research.
• Methodology – Note which methodology was used and why. Also, note any issues you feel arise due to the methodology. Again, you can use this to make an argument about gaps in the research.
• Quotations – Note down any quoteworthy lines you feel might be useful later.
• Notes – Make notes about anything not already covered. For example, linkages to or disagreements with other theories, questions raised but unanswered, shortcomings or limitations, and so forth.

If you’d like, you can try out our free catalog template here (see screenshot below).

2.3 – Digest and synthesise

Most importantly, as you work through the literature and build your catalogue, you need to synthesise all the information in your own mind – how does it all fit together? Look for links between the various articles and try to develop a bigger picture view of the state of the research. Some important questions to ask yourself are:

• What answers does the existing research provide to my own research questions ?
• Which points do the researchers agree (and disagree) on?
• How has the research developed over time?
• Where do the gaps in the current research lie?

To help you develop a big-picture view and synthesise all the information, you might find mind mapping software such as Freemind useful. Alternatively, if you’re a fan of physical note-taking, investing in a large whiteboard might work for you.

Step 3: Outline and write it up!

Once you’re satisfied that you have digested and distilled all the relevant literature in your mind, it’s time to put pen to paper (or rather, fingers to keyboard). There are two steps here – outlining and writing:

3.1 – Draw up your outline

Having spent so much time reading, it might be tempting to just start writing up without a clear structure in mind. However, it’s critically important to decide on your structure and develop a detailed outline before you write anything. Your literature review chapter needs to present a clear, logical and an easy to follow narrative – and that requires some planning. Don’t try to wing it!

Naturally, you won’t always follow the plan to the letter, but without a detailed outline, you’re more than likely going to end up with a disjointed pile of waffle , and then you’re going to spend a far greater amount of time re-writing, hacking and patching. The adage, “measure twice, cut once” is very suitable here.

In terms of structure, the first decision you’ll have to make is whether you’ll lay out your review thematically (into themes) or chronologically (by date/period). The right choice depends on your topic, research objectives and research questions, which we discuss in this article .

Once that’s decided, you need to draw up an outline of your entire chapter in bullet point format. Try to get as detailed as possible, so that you know exactly what you’ll cover where, how each section will connect to the next, and how your entire argument will develop throughout the chapter. Also, at this stage, it’s a good idea to allocate rough word count limits for each section, so that you can identify word count problems before you’ve spent weeks or months writing!

PS – check out our free literature review chapter template…

3.2 – Get writing

With a detailed outline at your side, it’s time to start writing up (finally!). At this stage, it’s common to feel a bit of writer’s block and find yourself procrastinating under the pressure of finally having to put something on paper. To help with this, remember that the objective of the first draft is not perfection – it’s simply to get your thoughts out of your head and onto paper, after which you can refine them. The structure might change a little, the word count allocations might shift and shuffle, and you might add or remove a section – that’s all okay. Don’t worry about all this on your first draft – just get your thoughts down on paper.

Once you’ve got a full first draft (however rough it may be), step away from it for a day or two (longer if you can) and then come back at it with fresh eyes. Pay particular attention to the flow and narrative – does it fall fit together and flow from one section to another smoothly? Now’s the time to try to improve the linkage from each section to the next, tighten up the writing to be more concise, trim down word count and sand it down into a more digestible read.

Once you’ve done that, give your writing to a friend or colleague who is not a subject matter expert and ask them if they understand the overall discussion. The best way to assess this is to ask them to explain the chapter back to you. This technique will give you a strong indication of which points were clearly communicated and which weren’t. If you’re working with Grad Coach, this is a good time to have your Research Specialist review your chapter.

Finally, tighten it up and send it off to your supervisor for comment. Some might argue that you should be sending your work to your supervisor sooner than this (indeed your university might formally require this), but in my experience, supervisors are extremely short on time (and often patience), so, the more refined your chapter is, the less time they’ll waste on addressing basic issues (which you know about already) and the more time they’ll spend on valuable feedback that will increase your mark-earning potential.

Literature Review Example

In the video below, we unpack an actual literature review so that you can see how all the core components come together in reality.

Let’s Recap

In this post, we’ve covered how to research and write up a high-quality literature review chapter. Let’s do a quick recap of the key takeaways:

• It is essential to understand the WHY of the literature review before you read or write anything. Make sure you understand the 4 core functions of the process.
• The first step is to hunt down the relevant literature . You can do this using Google Scholar, your university database, the snowballing technique and by reviewing other dissertations and theses.
• Next, you need to log all the articles in your reference manager , build your own catalogue of literature and synthesise all the research.
• Following that, you need to develop a detailed outline of your entire chapter – the more detail the better. Don’t start writing without a clear outline (on paper, not in your head!)
• Write up your first draft in rough form – don’t aim for perfection. Remember, done beats perfect.
• Refine your second draft and get a layman’s perspective on it . Then tighten it up and submit it to your supervisor.

Psst… there’s more!

This post is an extract from our bestselling short course, Literature Review Bootcamp . If you want to work smart, you don't want to miss this .

38 Comments

Thank you very much. This page is an eye opener and easy to comprehend.

This is awesome!

I wish I come across GradCoach earlier enough.

But all the same I’ll make use of this opportunity to the fullest.

Thank you for this good job.

Keep it up!

You’re welcome, Yinka. Thank you for the kind words. All the best writing your literature review.

Thank you for a very useful literature review session. Although I am doing most of the steps…it being my first masters an Mphil is a self study and one not sure you are on the right track. I have an amazing supervisor but one also knows they are super busy. So not wanting to bother on the minutae. Thank you.

You’re most welcome, Renee. Good luck with your literature review 🙂

This has been really helpful. Will make full use of it. 🙂

Thank you Gradcoach.

Really agreed. Admirable effort

thank you for this beautiful well explained recap.

Thank you so much for your guide of video and other instructions for the dissertation writing.

It is instrumental. It encouraged me to write a dissertation now.

Thank you the video was great – from someone that knows nothing thankyou

an amazing and very constructive way of presetting a topic, very useful, thanks for the effort,

It is timely

It is very good video of guidance for writing a research proposal and a dissertation. Since I have been watching and reading instructions, I have started my research proposal to write. I appreciate to Mr Jansen hugely.

I learn a lot from your videos. Very comprehensive and detailed.

Thank you for sharing your knowledge. As a research student, you learn better with your learning tips in research

I was really stuck in reading and gathering information but after watching these things are cleared thanks, it is so helpful.

Really helpful, Thank you for the effort in showing such information

This is super helpful thank you very much.

Thank you for this whole literature writing review.You have simplified the process.

I’m so glad I found GradCoach. Excellent information, Clear explanation, and Easy to follow, Many thanks Derek!

You’re welcome, Maithe. Good luck writing your literature review 🙂

Thank you Coach, you have greatly enriched and improved my knowledge

Great piece, so enriching and it is going to help me a great lot in my project and thesis, thanks so much

This is THE BEST site for ANYONE doing a masters or doctorate! Thank you for the sound advice and templates. You rock!

Thanks, Stephanie 🙂

This is mind blowing, the detailed explanation and simplicity is perfect.

I am doing two papers on my final year thesis, and I must stay I feel very confident to face both headlong after reading this article.

thank you so much.

if anyone is to get a paper done on time and in the best way possible, GRADCOACH is certainly the go to area!

This is very good video which is well explained with detailed explanation

Thank you excellent piece of work and great mentoring

Thanks, it was useful

Thank you very much. the video and the information were very helpful.

Good morning scholar. I’m delighted coming to know you even before the commencement of my dissertation which hopefully is expected in not more than six months from now. I would love to engage my study under your guidance from the beginning to the end. I love to know how to do good job

Thank you so much Derek for such useful information on writing up a good literature review. I am at a stage where I need to start writing my one. My proposal was accepted late last year but I honestly did not know where to start

Like the name of your YouTube implies you are GRAD (great,resource person, about dissertation). In short you are smart enough in coaching research work.

This is a very well thought out webpage. Very informative and a great read.

Very timely.

I appreciate.

Very comprehensive and eye opener for me as beginner in postgraduate study. Well explained and easy to understand. Appreciate and good reference in guiding me in my research journey. Thank you

Thank you. I requested to download the free literature review template, however, your website wouldn’t allow me to complete the request or complete a download. May I request that you email me the free template? Thank you.

Submit a Comment Cancel reply

Your email address will not be published. Required fields are marked *

Save my name, email, and website in this browser for the next time I comment.

• Print Friendly

• Resources Home 🏠
• Try SciSpace Copilot
• Search research papers
• Add Copilot Extension
• Try AI Detector
• Try Paraphraser
• Try Citation Generator
• April Papers
• June Papers
• July Papers

How To Write A Literature Review - A Complete Guide

Table of Contents

A literature review is much more than just another section in your research paper. It forms the very foundation of your research. It is a formal piece of writing where you analyze the existing theoretical framework, principles, and assumptions and use that as a base to shape your approach to the research question.

Curating and drafting a solid literature review section not only lends more credibility to your research paper but also makes your research tighter and better focused. But, writing literature reviews is a difficult task. It requires extensive reading, plus you have to consider market trends and technological and political changes, which tend to change in the blink of an eye.

Now streamline your literature review process with the help of SciSpace Copilot. With this AI research assistant, you can efficiently synthesize and analyze a vast amount of information, identify key themes and trends, and uncover gaps in the existing research. Get real-time explanations, summaries, and answers to your questions for the paper you're reviewing, making navigating and understanding the complex literature landscape easier.

In this comprehensive guide, we will explore everything from the definition of a literature review, its appropriate length, various types of literature reviews, and how to write one.

What is a literature review?

A literature review is a collation of survey, research, critical evaluation, and assessment of the existing literature in a preferred domain.

Eminent researcher and academic Arlene Fink, in her book Conducting Research Literature Reviews , defines it as the following:

“A literature review surveys books, scholarly articles, and any other sources relevant to a particular issue, area of research, or theory, and by so doing, provides a description, summary, and critical evaluation of these works in relation to the research problem being investigated.

Literature reviews are designed to provide an overview of sources you have explored while researching a particular topic, and to demonstrate to your readers how your research fits within a larger field of study.”

Simply put, a literature review can be defined as a critical discussion of relevant pre-existing research around your research question and carving out a definitive place for your study in the existing body of knowledge. Literature reviews can be presented in multiple ways: a section of an article, the whole research paper itself, or a chapter of your thesis.

A literature review does function as a summary of sources, but it also allows you to analyze further, interpret, and examine the stated theories, methods, viewpoints, and, of course, the gaps in the existing content.

As an author, you can discuss and interpret the research question and its various aspects and debate your adopted methods to support the claim.

What is the purpose of a literature review?

A literature review is meant to help your readers understand the relevance of your research question and where it fits within the existing body of knowledge. As a researcher, you should use it to set the context, build your argument, and establish the need for your study.

What is the importance of a literature review?

The literature review is a critical part of research papers because it helps you:

• Gain an in-depth understanding of your research question and the surrounding area
• Convey that you have a thorough understanding of your research area and are up-to-date with the latest changes and advancements
• Establish how your research is connected or builds on the existing body of knowledge and how it could contribute to further research
• Elaborate on the validity and suitability of your theoretical framework and research methodology
• Identify and highlight gaps and shortcomings in the existing body of knowledge and how things need to change
• Convey to readers how your study is different or how it contributes to the research area

How long should a literature review be?

Ideally, the literature review should take up 15%-40% of the total length of your manuscript. So, if you have a 10,000-word research paper, the minimum word count could be 1500.

Your literature review format depends heavily on the kind of manuscript you are writing — an entire chapter in case of doctoral theses, a part of the introductory section in a research article, to a full-fledged review article that examines the previously published research on a topic.

Another determining factor is the type of research you are doing. The literature review section tends to be longer for secondary research projects than primary research projects.

What are the different types of literature reviews?

All literature reviews are not the same. There are a variety of possible approaches that you can take. It all depends on the type of research you are pursuing.

Here are the different types of literature reviews:

Argumentative review

It is called an argumentative review when you carefully present literature that only supports or counters a specific argument or premise to establish a viewpoint.

Integrative review

It is a type of literature review focused on building a comprehensive understanding of a topic by combining available theoretical frameworks and empirical evidence.

Methodological review

This approach delves into the ''how'' and the ''what" of the research question —  you cannot look at the outcome in isolation; you should also review the methodology used.

Systematic review

This form consists of an overview of existing evidence pertinent to a clearly formulated research question, which uses pre-specified and standardized methods to identify and critically appraise relevant research and collect, report, and analyze data from the studies included in the review.

Meta-analysis review

Meta-analysis uses statistical methods to summarize the results of independent studies. By combining information from all relevant studies, meta-analysis can provide more precise estimates of the effects than those derived from the individual studies included within a review.

Historical review

Historical literature reviews focus on examining research throughout a period, often starting with the first time an issue, concept, theory, or phenomenon emerged in the literature, then tracing its evolution within the scholarship of a discipline. The purpose is to place research in a historical context to show familiarity with state-of-the-art developments and identify future research's likely directions.

Theoretical Review

This form aims to examine the corpus of theory accumulated regarding an issue, concept, theory, and phenomenon. The theoretical literature review helps to establish what theories exist, the relationships between them, the degree the existing approaches have been investigated, and to develop new hypotheses to be tested.

Scoping Review

The Scoping Review is often used at the beginning of an article, dissertation, or research proposal. It is conducted before the research to highlight gaps in the existing body of knowledge and explains why the project should be greenlit.

State-of-the-Art Review

The State-of-the-Art review is conducted periodically, focusing on the most recent research. It describes what is currently known, understood, or agreed upon regarding the research topic and highlights where there are still disagreements.

Can you use the first person in a literature review?

When writing literature reviews, you should avoid the usage of first-person pronouns. It means that instead of "I argue that" or "we argue that," the appropriate expression would be "this research paper argues that."

Do you need an abstract for a literature review?

Ideally, yes. It is always good to have a condensed summary that is self-contained and independent of the rest of your review. As for how to draft one, you can follow the same fundamental idea when preparing an abstract for a literature review. It should also include:

• The research topic and your motivation behind selecting it
• A one-sentence thesis statement
• An explanation of the kinds of literature featured in the review
• Summary of what you've learned
• Conclusions you drew from the literature you reviewed
• Potential implications and future scope for research

Here's an example of the abstract of a literature review

Is a literature review written in the past tense?

Yes, the literature review should ideally be written in the past tense. You should not use the present or future tense when writing one. The exceptions are when you have statements describing events that happened earlier than the literature you are reviewing or events that are currently occurring; then, you can use the past perfect or present perfect tenses.

How many sources for a literature review?

There are multiple approaches to deciding how many sources to include in a literature review section. The first approach would be to look level you are at as a researcher. For instance, a doctoral thesis might need 60+ sources. In contrast, you might only need to refer to 5-15 sources at the undergraduate level.

The second approach is based on the kind of literature review you are doing — whether it is merely a chapter of your paper or if it is a self-contained paper in itself. When it is just a chapter, sources should equal the total number of pages in your article's body. In the second scenario, you need at least three times as many sources as there are pages in your work.

Quick tips on how to write a literature review

To know how to write a literature review, you must clearly understand its impact and role in establishing your work as substantive research material.

You need to follow the below-mentioned steps, to write a literature review:

• Outline the purpose behind the literature review
• Search relevant literature
• Examine and assess the relevant resources
• Discover connections by drawing deep insights from the resources
• Structure planning to write a good literature review

1. Outline and identify the purpose of  a literature review

As a first step on how to write a literature review, you must know what the research question or topic is and what shape you want your literature review to take. Ensure you understand the research topic inside out, or else seek clarifications. You must be able to the answer below questions before you start:

• How many sources do I need to include?
• What kind of sources should I analyze?
• How much should I critically evaluate each source?
• Should I summarize, synthesize or offer a critique of the sources?
• Do I need to include any background information or definitions?

Additionally, you should know that the narrower your research topic is, the swifter it will be for you to restrict the number of sources to be analyzed.

2. Search relevant literature

Dig deeper into search engines to discover what has already been published around your chosen topic. Make sure you thoroughly go through appropriate reference sources like books, reports, journal articles, government docs, and web-based resources.

You must prepare a list of keywords and their different variations. You can start your search from any library’s catalog, provided you are an active member of that institution. The exact keywords can be extended to widen your research over other databases and academic search engines like:

• Google Scholar
• Microsoft Academic
• Science.gov

Besides, it is not advisable to go through every resource word by word. Alternatively, what you can do is you can start by reading the abstract and then decide whether that source is relevant to your research or not.

Additionally, you must spend surplus time assessing the quality and relevance of resources. It would help if you tried preparing a list of citations to ensure that there lies no repetition of authors, publications, or articles in the literature review.

3. Examine and assess the sources

It is nearly impossible for you to go through every detail in the research article. So rather than trying to fetch every detail, you have to analyze and decide which research sources resemble closest and appear relevant to your chosen domain.

While analyzing the sources, you should look to find out answers to questions like:

• What question or problem has the author been describing and debating?
• What is the definition of critical aspects?
• How well the theories, approach, and methodology have been explained?
• Whether the research theory used some conventional or new innovative approach?
• How relevant are the key findings of the work?
• In what ways does it relate to other sources on the same topic?
• What challenges does this research paper pose to the existing theory
• What are the possible contributions or benefits it adds to the subject domain?

Be always mindful that you refer only to credible and authentic resources. It would be best if you always take references from different publications to validate your theory.

Always keep track of important information or data you can present in your literature review right from the beginning. It will help steer your path from any threats of plagiarism and also make it easier to curate an annotated bibliography or reference section.

4. Discover connections

At this stage, you must start deciding on the argument and structure of your literature review. To accomplish this, you must discover and identify the relations and connections between various resources while drafting your abstract.

A few aspects that you should be aware of while writing a literature review include:

• Rise to prominence: Theories and methods that have gained reputation and supporters over time.
• Constant scrutiny: Concepts or theories that repeatedly went under examination.
• Contradictions and conflicts: Theories, both the supporting and the contradictory ones, for the research topic.
• Knowledge gaps: What exactly does it fail to address, and how to bridge them with further research?
• Influential resources: Significant research projects available that have been upheld as milestones or perhaps, something that can modify the current trends

Once you join the dots between various past research works, it will be easier for you to draw a conclusion and identify your contribution to the existing knowledge base.

5. Structure planning to write a good literature review

There exist different ways towards planning and executing the structure of a literature review. The format of a literature review varies and depends upon the length of the research.

Like any other research paper, the literature review format must contain three sections: introduction, body, and conclusion. The goals and objectives of the research question determine what goes inside these three sections.

Nevertheless, a good literature review can be structured according to the chronological, thematic, methodological, or theoretical framework approach.

Literature review samples

1. Standalone

2. As a section of a research paper

How SciSpace Discover makes literature review a breeze?

SciSpace Discover is a one-stop solution to do an effective literature search and get barrier-free access to scientific knowledge. It is an excellent repository where you can find millions of only peer-reviewed articles and full-text PDF files. Here’s more on how you can use it:

Find the right information

Find what you want quickly and easily with comprehensive search filters that let you narrow down papers according to PDF availability, year of publishing, document type, and affiliated institution. Moreover, you can sort the results based on the publishing date, citation count, and relevance.

Assess credibility of papers quickly

When doing the literature review, it is critical to establish the quality of your sources. They form the foundation of your research. SciSpace Discover helps you assess the quality of a source by providing an overview of its references, citations, and performance metrics.

Get the complete picture in no time

SciSpace Discover’s personalized suggestion engine helps you stay on course and get the complete picture of the topic from one place. Every time you visit an article page, it provides you links to related papers. Besides that, it helps you understand what’s trending, who are the top authors, and who are the leading publishers on a topic.

Make referring sources super easy

To ensure you don't lose track of your sources, you must start noting down your references when doing the literature review. SciSpace Discover makes this step effortless. Click the 'cite' button on an article page, and you will receive preloaded citation text in multiple styles — all you've to do is copy-paste it into your manuscript.

Final tips on how to write a literature review

A massive chunk of time and effort is required to write a good literature review. But, if you go about it systematically, you'll be able to save a ton of time and build a solid foundation for your research.

We hope this guide has helped you answer several key questions you have about writing literature reviews.

Would you like to explore SciSpace Discover and kick off your literature search right away? You can get started here .

Frequently Asked Questions (FAQs)

1. how to start a literature review.

• What questions do you want to answer?

• What sources do you need to answer these questions?

• What information do these sources contain?

• How can you use this information to answer your questions?

2. What to include in a literature review?

• A brief background of the problem or issue

• What has previously been done to address the problem or issue

• A description of what you will do in your project

• How this study will contribute to research on the subject

3. Why literature review is important?

The literature review is an important part of any research project because it allows the writer to look at previous studies on a topic and determine existing gaps in the literature, as well as what has already been done. It will also help them to choose the most appropriate method for their own study.

4. How to cite a literature review in APA format?

To cite a literature review in APA style, you need to provide the author's name, the title of the article, and the year of publication. For example: Patel, A. B., & Stokes, G. S. (2012). The relationship between personality and intelligence: A meta-analysis of longitudinal research. Personality and Individual Differences, 53(1), 16-21

5. What are the components of a literature review?

• A brief introduction to the topic, including its background and context. The introduction should also include a rationale for why the study is being conducted and what it will accomplish.

• A description of the methodologies used in the study. This can include information about data collection methods, sample size, and statistical analyses.

• A presentation of the findings in an organized format that helps readers follow along with the author's conclusions.

6. What are common errors in writing literature review?

• Not spending enough time to critically evaluate the relevance of resources, observations and conclusions.

• Totally relying on secondary data while ignoring primary data.

• Letting your personal bias seep into your interpretation of existing literature.

• No detailed explanation of the procedure to discover and identify an appropriate literature review.

7. What are the 5 C's of writing literature review?

• Cite - the sources you utilized and referenced in your research.

• Compare - existing arguments, hypotheses, methodologies, and conclusions found in the knowledge base.

• Contrast - the arguments, topics, methodologies, approaches, and disputes that may be found in the literature.

• Critique - the literature and describe the ideas and opinions you find more convincing and why.

• Connect - the various studies you reviewed in your research.

8. How many sources should a literature review have?

When it is just a chapter, sources should equal the total number of pages in your article's body. if it is a self-contained paper in itself, you need at least three times as many sources as there are pages in your work.

9. Can literature review have diagrams?

• To represent an abstract idea or concept

• To explain the steps of a process or procedure

• To help readers understand the relationships between different concepts

10. How old should sources be in a literature review?

Sources for a literature review should be as current as possible or not older than ten years. The only exception to this rule is if you are reviewing a historical topic and need to use older sources.

11. What are the types of literature review?

• Argumentative review

• Integrative review

• Methodological review

• Systematic review

• Meta-analysis review

• Historical review

• Theoretical review

• Scoping review

• State-of-the-Art review

12. Is a literature review mandatory?

Yes. Literature review is a mandatory part of any research project. It is a critical step in the process that allows you to establish the scope of your research, and provide a background for the rest of your work.

But before you go,

• Six Online Tools for Easy Literature Review
• Evaluating literature review: systematic vs. scoping reviews
• Systematic Approaches to a Successful Literature Review
• Writing Integrative Literature Reviews: Guidelines and Examples

You might also like

Consensus GPT vs. SciSpace GPT: Choose the Best GPT for Research

Literature Review and Theoretical Framework: Understanding the Differences

Types of Essays in Academic Writing - Quick Guide (2024)

• Research Consultation
• How-to Guides
• People Search
• Library Databases
• Research Guides
• Find Periodicals
• Google Scholar
• Library Map
• Interlibrary Loan - ILL
• Research & Instruction
• Computers and Laptops
• Services For...
• Reserve a Room
• APSU Records Management
• Library Collections
• Digital Collections
• Special Collections
• Veterans' Oral History
• Government Resources
• Subject Librarians
• Library Information
• Woodward Library Society
• New @ Woodward Library
• Celebration of Scholarship
• Join Woodward Library Society

Writing a Literature Review: Examples & Tutorials

• Phase 1: Scope of Review
• Phase 2: Finding Information
• Phase 3: Recording Information
• Phase 4: Evaluating Information
• Phase 5: Organizing the Review
• Phase 6: Writing the Review & Bibliography
• Tools & Resources
• Examples & Tutorials

Examples of Lit. Reviews

Sample Literature Review -Here is a sample literature review written by a librarian at American University Library.

Deshmukh, Marion F. " The Visual Arts and Cultural Migration in the 1930s and 1940s: A Literature Review. " Central European History (Cambridge University Press / UK) 41.4 (2008): 569-604. Dunjó, Jordi, et al. " Hazard and Operability (HAZOP) Analysis. A Literature Review ." Journal of Hazardous Materials 173.1-3 (2010): 19-32. Gibbons, Susan. " Understanding Empathy as a Complex Construct: A Review of the Literature ." Clinical Social Work Journal 39.3 (2011): 243-52.

Liddle, H. A. (2004). Family-based therapies for adolescent alcohol and drug use: Research contributions and future research needs.   Addiction , 99 (Suppl.2), 76-92.

Mayer, David J. " Acupuncture: An Evidence-Based Review of the Clinical Literature ." Annual Review of Medicine 51:1 (2000): 49-63.

Meyer, Sebastian, Bruno Glaser, and Peter Quicker. " Technical, Economical, and Climate-Related Aspects of Biochar Production Technologies: A Literature Review. " Environmental science & technology 45.22 (2011): 9473-83.

• Writing the Literature Review Part I Defines what a literature review is - and is not.
• Writing the Literature Review Part II Organizing sources, basic steps in the writing process.
• Literature Review Overview for Graduate Students Understand how studies relate to one another, how your own ideas fit within the existing literature.
• Interactive tutorial for literature reviews in Education & Behavioral Sciences • Understanding the Literature Review • Identifying Sources for the Literature Review • Finding Review and Research Articles • Putting it All Together

Literature Review Overview

Subject Guide

• << Previous: Tools & Resources
• Last Updated: Oct 17, 2023 12:56 PM
• URL: https://libguides.apsu.edu/litreview

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, automatically generate references for free.

• Knowledge Base
• Dissertation
• What is a Literature Review? | Guide, Template, & Examples

What is a Literature Review? | Guide, Template, & Examples

Published on 22 February 2022 by Shona McCombes . Revised on 7 June 2022.

What is a literature review? A literature review is a survey of scholarly sources on a specific topic. It provides an overview of current knowledge, allowing you to identify relevant theories, methods, and gaps in the existing research.

There are five key steps to writing a literature review:

• Search for relevant literature
• Evaluate sources
• Identify themes, debates and gaps
• Outline the structure
• Write your literature review

A good literature review doesn’t just summarise sources – it analyses, synthesises, and critically evaluates to give a clear picture of the state of knowledge on the subject.

Instantly correct all language mistakes in your text

Be assured that you'll submit flawless writing. Upload your document to correct all your mistakes.

Table of contents

Why write a literature review, examples of literature reviews, step 1: search for relevant literature, step 2: evaluate and select sources, step 3: identify themes, debates and gaps, step 4: outline your literature review’s structure, step 5: write your literature review, frequently asked questions about literature reviews, introduction.

• Quick Run-through
• Step 1 & 2

When you write a dissertation or thesis, you will have to conduct a literature review to situate your research within existing knowledge. The literature review gives you a chance to:

• Demonstrate your familiarity with the topic and scholarly context
• Develop a theoretical framework and methodology for your research
• Position yourself in relation to other researchers and theorists
• Show how your dissertation addresses a gap or contributes to a debate

You might also have to write a literature review as a stand-alone assignment. In this case, the purpose is to evaluate the current state of research and demonstrate your knowledge of scholarly debates around a topic.

The content will look slightly different in each case, but the process of conducting a literature review follows the same steps. We’ve written a step-by-step guide that you can follow below.

Prevent plagiarism, run a free check.

Writing literature reviews can be quite challenging! A good starting point could be to look at some examples, depending on what kind of literature review you’d like to write.

• Example literature review #1: “Why Do People Migrate? A Review of the Theoretical Literature” ( Theoretical literature review about the development of economic migration theory from the 1950s to today.)
• Example literature review #2: “Literature review as a research methodology: An overview and guidelines” ( Methodological literature review about interdisciplinary knowledge acquisition and production.)
• Example literature review #3: “The Use of Technology in English Language Learning: A Literature Review” ( Thematic literature review about the effects of technology on language acquisition.)
• Example literature review #4: “Learners’ Listening Comprehension Difficulties in English Language Learning: A Literature Review” ( Chronological literature review about how the concept of listening skills has changed over time.)

You can also check out our templates with literature review examples and sample outlines at the links below.

Download Word doc Download Google doc

Before you begin searching for literature, you need a clearly defined topic .

If you are writing the literature review section of a dissertation or research paper, you will search for literature related to your research objectives and questions .

If you are writing a literature review as a stand-alone assignment, you will have to choose a focus and develop a central question to direct your search. Unlike a dissertation research question, this question has to be answerable without collecting original data. You should be able to answer it based only on a review of existing publications.

Make a list of keywords

Start by creating a list of keywords related to your research topic. Include each of the key concepts or variables you’re interested in, and list any synonyms and related terms. You can add to this list if you discover new keywords in the process of your literature search.

• Social media, Facebook, Instagram, Twitter, Snapchat, TikTok
• Body image, self-perception, self-esteem, mental health
• Generation Z, teenagers, adolescents, youth

Search for relevant sources

Use your keywords to begin searching for sources. Some databases to search for journals and articles include:

• Your university’s library catalogue
• Google Scholar
• Project Muse (humanities and social sciences)
• Medline (life sciences and biomedicine)
• EconLit (economics)
• Inspec (physics, engineering and computer science)

You can use boolean operators to help narrow down your search:

Read the abstract to find out whether an article is relevant to your question. When you find a useful book or article, you can check the bibliography to find other relevant sources.

To identify the most important publications on your topic, take note of recurring citations. If the same authors, books or articles keep appearing in your reading, make sure to seek them out.

You probably won’t be able to read absolutely everything that has been written on the topic – you’ll have to evaluate which sources are most relevant to your questions.

For each publication, ask yourself:

• What question or problem is the author addressing?
• What are the key concepts and how are they defined?
• What are the key theories, models and methods? Does the research use established frameworks or take an innovative approach?
• What are the results and conclusions of the study?
• How does the publication relate to other literature in the field? Does it confirm, add to, or challenge established knowledge?
• How does the publication contribute to your understanding of the topic? What are its key insights and arguments?
• What are the strengths and weaknesses of the research?

Make sure the sources you use are credible, and make sure you read any landmark studies and major theories in your field of research.

You can find out how many times an article has been cited on Google Scholar – a high citation count means the article has been influential in the field, and should certainly be included in your literature review.

The scope of your review will depend on your topic and discipline: in the sciences you usually only review recent literature, but in the humanities you might take a long historical perspective (for example, to trace how a concept has changed in meaning over time).

Remember that you can use our template to summarise and evaluate sources you’re thinking about using!

Take notes and cite your sources

As you read, you should also begin the writing process. Take notes that you can later incorporate into the text of your literature review.

It’s important to keep track of your sources with references to avoid plagiarism . It can be helpful to make an annotated bibliography, where you compile full reference information and write a paragraph of summary and analysis for each source. This helps you remember what you read and saves time later in the process.

You can use our free APA Reference Generator for quick, correct, consistent citations.

To begin organising your literature review’s argument and structure, you need to understand the connections and relationships between the sources you’ve read. Based on your reading and notes, you can look for:

• Trends and patterns (in theory, method or results): do certain approaches become more or less popular over time?
• Themes: what questions or concepts recur across the literature?
• Debates, conflicts and contradictions: where do sources disagree?
• Pivotal publications: are there any influential theories or studies that changed the direction of the field?
• Gaps: what is missing from the literature? Are there weaknesses that need to be addressed?

This step will help you work out the structure of your literature review and (if applicable) show how your own research will contribute to existing knowledge.

• Most research has focused on young women.
• There is an increasing interest in the visual aspects of social media.
• But there is still a lack of robust research on highly-visual platforms like Instagram and Snapchat – this is a gap that you could address in your own research.

There are various approaches to organising the body of a literature review. You should have a rough idea of your strategy before you start writing.

Depending on the length of your literature review, you can combine several of these strategies (for example, your overall structure might be thematic, but each theme is discussed chronologically).

Chronological

The simplest approach is to trace the development of the topic over time. However, if you choose this strategy, be careful to avoid simply listing and summarising sources in order.

Try to analyse patterns, turning points and key debates that have shaped the direction of the field. Give your interpretation of how and why certain developments occurred.

If you have found some recurring central themes, you can organise your literature review into subsections that address different aspects of the topic.

For example, if you are reviewing literature about inequalities in migrant health outcomes, key themes might include healthcare policy, language barriers, cultural attitudes, legal status, and economic access.

Methodological

If you draw your sources from different disciplines or fields that use a variety of research methods , you might want to compare the results and conclusions that emerge from different approaches. For example:

• Look at what results have emerged in qualitative versus quantitative research
• Discuss how the topic has been approached by empirical versus theoretical scholarship
• Divide the literature into sociological, historical, and cultural sources

Theoretical

A literature review is often the foundation for a theoretical framework . You can use it to discuss various theories, models, and definitions of key concepts.

You might argue for the relevance of a specific theoretical approach, or combine various theoretical concepts to create a framework for your research.

Like any other academic text, your literature review should have an introduction , a main body, and a conclusion . What you include in each depends on the objective of your literature review.

The introduction should clearly establish the focus and purpose of the literature review.

If you are writing the literature review as part of your dissertation or thesis, reiterate your central problem or research question and give a brief summary of the scholarly context. You can emphasise the timeliness of the topic (“many recent studies have focused on the problem of x”) or highlight a gap in the literature (“while there has been much research on x, few researchers have taken y into consideration”).

Depending on the length of your literature review, you might want to divide the body into subsections. You can use a subheading for each theme, time period, or methodological approach.

As you write, make sure to follow these tips:

• Summarise and synthesise: give an overview of the main points of each source and combine them into a coherent whole.
• Analyse and interpret: don’t just paraphrase other researchers – add your own interpretations, discussing the significance of findings in relation to the literature as a whole.
• Critically evaluate: mention the strengths and weaknesses of your sources.
• Write in well-structured paragraphs: use transitions and topic sentences to draw connections, comparisons and contrasts.

In the conclusion, you should summarise the key findings you have taken from the literature and emphasise their significance.

If the literature review is part of your dissertation or thesis, reiterate how your research addresses gaps and contributes new knowledge, or discuss how you have drawn on existing theories and methods to build a framework for your research. This can lead directly into your methodology section.

A literature review is a survey of scholarly sources (such as books, journal articles, and theses) related to a specific topic or research question .

It is often written as part of a dissertation , thesis, research paper , or proposal .

There are several reasons to conduct a literature review at the beginning of a research project:

• To familiarise yourself with the current state of knowledge on your topic
• To ensure that you’re not just repeating what others have already done
• To identify gaps in knowledge and unresolved problems that your research can address
• To develop your theoretical framework and methodology
• To provide an overview of the key findings and debates on the topic

Writing the literature review shows your reader how your work relates to existing research and what new insights it will contribute.

The literature review usually comes near the beginning of your  dissertation . After the introduction , it grounds your research in a scholarly field and leads directly to your theoretical framework or methodology .

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

McCombes, S. (2022, June 07). What is a Literature Review? | Guide, Template, & Examples. Scribbr. Retrieved 26 August 2024, from https://www.scribbr.co.uk/thesis-dissertation/literature-review/

Is this article helpful?

Shona McCombes

Other students also liked, how to write a dissertation proposal | a step-by-step guide, what is a theoretical framework | a step-by-step guide, what is a research methodology | steps & tips.