Exploring Generative AI and Natural Language Processing to Develop Search Strategies for Systematic Reviews
- Conference
- Location
-
Portland, Oregon
- Publication Date
-
June 23, 2024
- Start Date
-
June 23, 2024
- End Date
-
July 12, 2024
- Conference Session
- Tagged Division
-
Engineering Libraries Division (ELD)
- Permanent URL
-
https://peer.asee.org/47414
Paper Authors
Sarah G. Park
University of Illinois at Urbana - Champaign
orcid.org/0000-0002-5052-7252
Sarah Park is the Mathematics and Computational Sciences Librarian and Head of the Mathematics Library at the University of Illinois at Urbana-Champaign. She supports active engagement with faculty, students, and staff to promote library services and collections and to support emerging information literacy.
Monica Carroll University of Illinois at Urbana - Champaign
Monica Carroll is an Engineering Librarian at the University of Illinois at Urbana-Champaign. Originally trained as a geologist, she is interested in the sociology and social history of academic research in STEM disciplines.
Lucy Marie Alice Esteve Duke University
Lucy Esteve is an Endocrinology Research Fellow in the Department of Medicine at Duke University. Her academic interests focus on the use of technology (in particular wearable smartwatches) for early detection of diabetes and prevention of diabetes-related complications.
Karnika Singh Duke University
Karnika Singh is a PhD candidate in Biomedical Engineering at Duke University. Her research is focused on the use of digital health technologies for health monitoring.
Abstract
Systematic reviews, as well as other comprehensive literature reviews, require a rigorous and structured approach for an exhaustive literature search. Identifying the relevant keywords that encapsulate the research topic and then combining them using the appropriate search technique demands expertise in both search techniques and in-depth domain knowledge. As a result, librarians are frequently asked to join research teams to assist researchers unfamiliar with this intricate process. These subject specialists have expertise in using search tools and techniques to formulate search statements, yet they often need to conduct extensive literature surveys to identify relevant search terms, especially in rapidly evolving fields. Although controlled vocabularies and keywords supplied by authors and database companies are useful, they are often insufficient in capturing all relevant terms used in the literature. This paper explores how Generative Artificial Intelligence (AI) and Natural Language Processing (NLP) could be harnessed by librarians to refine the formulation of search terms for these reviews. This pilot study suggests that the use of Generative AI and NLP helps users identify relevant search terms for developing search strategies, although users must be cautious about the reproducibility of Generative AI's responses.
Park, S. G., & Carroll, M., & Esteve, L. M. A., & Singh, K. (2024, June), Exploring Generative AI and Natural Language Processing to Develop Search Strategies for Systematic Reviews Paper presented at 2024 ASEE Annual Conference & Exposition, Portland, Oregon. https://peer.asee.org/47414
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2024 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015