Using Ai Tools in the Research ProcessAi tools can assist with various tasks within the research process, from brainstorming topics and generating keywords, to assisting with literature searching, including literature reviews, summarizing sources or text/ data analysis, and more.
Generative AI can be a helpful tool for brainstorming during the research process. Here are a few tips that will help you use AI tools like ChatGPT for brainstorming topics and keywords for research.
1. Define your general topic area.
2. Choose your AI tool (such as ChatGPT).
3. Craft your prompt, clearly specifying your request. For example, you can ask the AI to generate ideas for research questions or propose methodologies or recommend scholarly databases. See our guide on Creating Effective Prompts.
4. Experiment and refine your prompt, building on what was helpful or not helpful about the response given.
5. Critically evaluate and filter the results using your human expertise, knowledge, and experience. Validate using credible sources.
6. Beware of ethical considerations such as bias, source, privacy, and citing the use of AI according The Chicago School's policy on Academic Ethics, Integrity, and Responsibility as outlined in the Chicago School Catalog, under Student Rights & Responsibilities.
One of the best ways to ensure relevant and comprehensive results from your library searches is to collect a good list of keywords pertaining to your research topic. In addition to using your own knowledge and judgement, consulting with your librarians, database thesauri, and other experts in your field, you can use AI for quick and easy help generating keywords.
Introduction:
Ask for Suggestions:
Review and Refine:
Ask Follow-up Questions:
Validate the Results and Consult Existing Literature:
Iterative Process:
Generative Ai has introduced new tools available to researchers, enabling users to visualize connections between works, or facilitate evaluation and synthesis of relevant works.
These tools are best used a supplement to the literature review process.They do not search all relevant literature, and are not meant to substitute library database searching. It's important to always verify the information by referring to the actual article.
SciteAi is an AI-powered research platform that analyzes and provides citation context for scientific papers, helping researchers evaluate the credibility and impact of scholarly articles. Some key features include:
Bakker, C., Theis-Mahon, N., & Brown, S. J. (2023). Evaluating the Accuracy of scite, a Smart Citation Index. Hypothesis: Research Journal for Health Information Professionals, 35(2). https://doi.org/10.18060/26528
Keenious is a resource recommender tool designed to aid in the identification and discovery of scholarly research. It analyzes writing from text documents and PDFs to recommend the most relevant articles and topics to explore using artificial intelligence combined with conventional search algorithms.Keenious is available via a web browser for content uploads and text input, and can also be used as an add-on in Microsoft Word or Google Docs.
ResearchRabbit is a “citation-based literature mapping tool” available online. It aims to optimize your time searching for references as you start planning your project, or literature review. You start by using one or more papers (called seed papers), and the app will find more papers relevant to the topic of interest (which is dictated by the seed papers you previously selected).
TIP: While ResearchRabbit claims to cover 100s of millions of academic articles or more than 90%+ of materials that can be found in major databases used by academic institutions, it's best used in conjunction with searching within library databases. It helps you visualize the connections between areas of research, and it can help you discover works that you may have missed in your previous searches.
Elicit uses Chat GPT-4 to automate parts of the workflow for literature review searching. If you ask it a question, it will how relevant papers and summaries of key information about those papers in table format, including summaries of study limitations, outcomes, etc. This tool is free up to a certain amount of "credits." Users then pay for additional credits.
Note: the library is still developing this page, check back later for more information!
It can be difficult to know how if the content AI produces is from a valid source that can be used for research. The Association of College & Research Libraries (ACRL) provides these steps on evaluating sources found from AI tools.
"1. Are the citations actually real? Does such a journal/website/book exist? State which are not real, and which are real. State whether any website used in a real citation where you found it is credible and why.
2. State where those specific real citations are available full text (check our library databases too). List the names of the places you found them (for example, name of such-and-such website, name of database, etc...).
3. Check the credentials of the lead author by doing a google search of their name in quotes. Are they trained in the field of the topic? State their credentials and/or academic degrees.
4. Now run their name (in quote marks) in a library database (like ProQuest or EBSCOhost), use a drop down to search for AUTHOR - do they appear? IF YES, what are their other article/s (provide the permalink URLs) about?
5. Now run a search for your same chosen topic in a library database. What are the top four most relevant (provide the four permalink URLs)? Note if they match any of the original four generated.
Bonus 1 point: Talk about paid and unpaid access to this AI tool (look at pricing for different versions on the ChatGPT website) and how YOU think it might affect what you find in any tier of paid/unpaid access."
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
“Vetting ChatGPT Sources | ACRL Framework for Information Literacy Sandbox.” Retrieved January 22, 2024, from Vetting ChatGPT sources | ACRL Framework for Information Literacy Sandbox
