Skip to Main Content

Copy of ECON 3495 Applied Data Science in Economics

What is a Literature Review

A literature review compiles and examines scholarly articles, books, and other relevant sources within a specific area or sub-area to comprehensively summarize the key findings and discussions on a subject. This review can either stand as an independent document or form a section or chapter of a thesis or research paper related to the subject. The objectives of conducting a literature review include:

  • Concisely summarizing the existing research within the field.
  • Assessing the credibility of the evidence and the claims' validity.
  • Demonstrating the relationships between various published works.
  • Situating your own research amongst the broader scholarly conversations in the field.

A literature review merges the summarization and synthesis of the discussed literature. It outlines the key points from sources relevant to your topic and identifies any potential gaps in the literature.


Question to Consider

  1. How does my literature review contribute to clarifying the specific thesis, problem, or research question under investigation?
  2. What kind of literature review am I undertaking? Is it focused on theoretical issues, methodologies, policy analysis, quantitative evidence (for example, evaluating the efficacy of a new intervention), or qualitative insights (such as examining the experiences of loneliness among migrant workers)?
  3. What is the extent of my literature review's coverage?
  4. What kinds of sources am I incorporating in my review (for instance, academic journals, books, government reports, or mass media)?
  5. How effective was my approach to gathering information? Was my search comprehensive enough to capture all pertinent material? Was it sufficiently focused on omitting irrelevant information? Is the volume of sources I've consulted appropriate for the length of my paper?
  6. Have I engaged in a critical analysis of the sources I've reviewed? Do I approach the literature with a specific set of concepts and questions, making comparisons across different sources based on how they address these issues? Rather than merely listing and summarizing sources, have I evaluated them, highlighting their strengths and limitations?
  7. Have I acknowledged and discussed research findings that challenge my own viewpoint?
  8. Will readers find my literature review to be relevant, appropriate, and beneficial?


Online Resources to get started


AI Resources to help with Creating a Literature Review

Resource table created by Georgetown University Library

Elicit Using large language models (LLMs), Elicit finds papers relevant to your topic by searching through papers and citations and extracting and synthesizing key information. Semantic Scholar Database Free trial available. Pay for credits after trial expires. Elicit FAQs (older version FAQs)
Perplexity Using LLMs, perplexity is a search engine that provides AI-generated answers (much like ChatGPT), including citations which are linked above the summaries. Internal search index Free with paid subscriptions available. Perplexity FAQs
Consensus Similar to Elicit, Consensus uses LLMs to help researchers find and synthesize answers to research questions, focusing on the scholarly authors' findings and claims in each paper. Semantic Scholar Database Free (20 searches/month); Paid version allows unlimited searching. Consensus FAQs
Semantic Scholar Semantic Scholar (which supplies underlying data for many of the other tools on this list) provides brief summaries ('TLDR's) of the main objectives and results of papers. Semantic Scholar Database Semantic Scholar is currently free. Semantic Scholar FAQs
Research Rabbit Research Rabbit is a citation-based mapping tool that focuses on the relationships between research works. It uses visualizations to help researchers find similar papers and other researchers in their field. Research Rabbit uses multiple databases but does not name them (more information can be found on the FAQ page). Research Rabbit is currently free. Research Rabbit FAQs
Connected Papers Like Research Rabbit, Connected Papers focuses on the relationships between research papers to find similar research. You can also use Connected Papers to get a visual overview of an academic field. Semantic Scholar Database Free (5 graphs/month); paid version allows unlimited graphing. Connected Papers - About
scite scite has a suite of products that help researchers develop their topics, find papers, and search citations in context (describing whether the article provides supporting or contrasting evidence)  Many different sources (an incomplete list can be found on this page) No. (Pricing information) scite FAQshow scite works
Scholarcy Scholarcy summarizes key points and claims of articles into 'summary cards' that researchers can read, share, and annotate when compiling research on a given topic. Scholarcy only uses research papers uploaded or linked by the researcher themselves. It works as a way to help you read and summarize your research but is not a search engine. Free (short articles only); Paid version allows articles of any length. Scholarcy FAQs
ChatGPT While the AI chatbot ChatGPT is typically thought of as a writing tool, it can be used in the initial idea development phase of research, and can also be of use in finding further sources. (Remember to always look up sources to verify their credibility.) The paid versions of ChatGPT are currently connected to the internet through Bing. The free version was trained on data last updated in September 2021, but that is likely to change. There is a free version available. OpenAI Help Center - ChatGPT
Gemini Designed by Google, Gemini (formerly Bard) is an AI-powered chatbot that responds to natural language queries with relevant information. As with ChatGPT, researchers can use Gemini to aid in topic development and initial source discovery. Gemini can currently connect to the Internet. Gemini is currently free to use. (Personal Google account required, does not work with GU accounts.) Gemini FAQ
Directions from Professor Santiago García-Couto
Literature Review
A literature review pursues the following goals:
1. identify the literature related to the research question
2. summarize the literature related to the research question,
3. highlight the contribution of the research question to the literature.
When you discuss the literature related to a research question, you should start from the broad areas and then go into the more specific areas. You can think of this as if the broad areas were the trunk of a tree and the more specific areas are branches. Nevertheless, when writing your literature review, you should prioritize the strands of literature, i.e., branches, that are more directly related to your paper. Of course, depending on the topic that you select, there might be more than one broad area of research and more than one specific branch.
Let's consider the question, "what is the effect of investments in automating industrial production processes in Uruguay on the wages of low-skilled workers since the year 2000?" In this case, I would start considering all the research that discusses how technology and investments in a certain type of capital, preferably automation, affect workers. Then I would focus on the effect of automating industrial processes, both in developed and developing economies and in any period. After this, I would look into those studies that focus on wages and low-skilled workers, and then I would try to find any studies that analyze this in developing economies, particularly in Latin America and Uruguay. Finally, I would discuss the literature related to the specific methods/empirical strategy that I plan to use to tackle this question. In my case, I would probably consider the task approach to labor markets, and I would cite papers from this literature that deal with the effect of automation on workers (e.g., Acemoglu and Restrepo, 2019).
The most effective way to find papers that are related to each other and that belong to similar strands of literature is to follow the citations of the papers we find, to see which How to?: Literature Review 2 papers cite the ones that we find, and to identify and follow the research of experts in the topics we are looking at.
Once we have found the academic articles that are related to our research question, we should summarize them to extract relevant information to identify the main questions, methods, data, and contributions of the literature and to aid the writing of our literature review.
The next step is to identify how the papers that we have selected are related and how they complement each other. This will allow us to see how our knowledge on these topics has evolved over time and to identify how our research question can help us increase our knowledge on the subject. You can think of this as if you were telling the story of this strand of literature as if you were a biographer.
Finally, we will use the summaries and the relationships we have identified across the literature as our input to write one cohesive document. Our literature review must summarize and relate the most important contributions within each of the strands of literature that we have analyzed, relate these strands of literature to each other, and point out how our research question fits within the literature and how it broadens our knowledge of the issues analyzed.
Methods and Tools
You should be eclectic and extensively search different sources using several tools to ensure you have included all the relevant references. It is important that the literature review is very comprehensive, to make sure of the contribution of addressing the research question and not to leave out important contributions that could guide how you address your question.
The most common resource to search for articles and working papers in economics is IDEAS/RePec. Nevertheless, you should also consider using Google Scholar and Scopus and searching directly on Google. You will be able to access most of the articles published in academic journals through the GU-Q Library. I strongly recommend you use the Lean Library Extension on your web browser, which will tell you if an article is available at our library. Several AI tools seem particularly promising to complement web searches to find literature relevant to our research question, to understand how different papers are How to?: Literature Review 3 related to each other, and to summarize the contribution of each article. We should incorporate them in our analysis as they can help us to be more efficient.
These some tools that seem to be particularly interesting:
  • Elicit: search, summarize, extract information, and relate research papers.
  • Scispace: search, summarize, extract information and related research papers.
  • Scite: research assistant that generates literature reviews based on specific research questions and research papers.
  • ResearchRabbit: relate papers to each other and identify literature strands visually.
  • ChatPDF: analyze and extract information from PDFs by asking questions to it.
  • Consensus: a search engine that finds insights in research papers.
Summary of Papers
In our summary of the research papers, we should include the following points:
  • Research Question: what is the question that the authors address?
  • Motivation: why is this an interesting/important question? Why is it worth addressing it? What can we learn from addressing it?
  • Conceptual Framework/Theory: what are the main theoretical tools that the authors use to address the question? What are the conceptual framework's main characteristics (e.g., environment, agents, endowments)? What are the choices and trade-offs that agents face? What are the characteristics of the equilibrium of the model? What are the main mechanisms that allow us to analyze and answer the research question? What are the main hypotheses about the parameters of the model, the behavior of economic agents and the main mechanisms of the model to answer the research question?
  • Data: what data sources do the authors use to document the evidence presented and address the question? What are the key variables that the authors select or construct? What methodology do the authors follow to construct these variables? How to?: Literature Review 4
  • Empirical strategy/identification: how do the authors bring the conceptual framework to the data? Does the paper use a reduced form or a structural form model? What variables are assumed to be endogenous/dependent, and what are assumed to be exogenous/independent? What are the main identifying assumptions? What are the main limitations of the strategy?
    • Discussion on Structural and Reduced form models.
    • 1-Structural_vs_Reduced_TML_v2023.pdf
    • Results: what are the key findings related to the research question? Implications and contribution: what are the main takeaways from the article? What have we learned that is relevant for policymakers and for the public in general?
Quality of Sources
You must assess the quality of the articles you select to discuss in the literature review. Articles published in top journals and with many citations should have a more prominent role in the review. You can check the number of citations on Google Scholar, and here you can find a popular ranking of journals in Economics. Additionally, you should also include working papers from authors who have been successful in publishing or who are affiliated with top research institutions. Here, you can find a ranking of top economic researchers, research institutions, and economic departments. Of course, different institutions and authors are particularly good in specific fields, so part of your task is to identify who these are for our topic.
You should follow the Chicago Manual of Style Author-Date system to list your bibliographical references.