Back to Search Start Over

An Empirical Study Evaluating ChatGPT's Performance in Generating Search Strategies for Systematic Reviews.

Authors :
Yu, Fei
Kincaide, Heather
Carlson, Rebecca Beth
Source :
Proceedings of the Association for Information Science & Technology. Oct2024, Vol. 61 Issue 1, p423-434. 12p.
Publication Year :
2024

Abstract

This study evaluated the performance of ChatGPT‐3.5 and ChatGPT‐4 in developing search strategies for systematic reviews. Using the Peer Review of Electronic Search Strategies (PRESS) framework, we employed a two‐round testing format for each version. In the first round, both versions displayed comparable competencies when assessed quantitatively by the PRESS measures. However, qualitative feedback from two professional health sciences librarians indicated that ChatGPT‐4 outperformed ChatGPT‐3.5, particularly in suggesting MeSH term inclusion and refining search strategy formulations. In the second round, prompts were refined based on the feedback from the previous round of testing. Both qualitative and quantitative evaluation results confirmed ChatGPT‐4's superiority. This study provides empirical evidence of advancements in language model capabilities, highlighting ChatGPT‐4's enhanced efficiency and accuracy in developing search strategies for systematic reviews. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
23739231
Volume :
61
Issue :
1
Database :
Academic Search Index
Journal :
Proceedings of the Association for Information Science & Technology
Publication Type :
Conference
Accession number :
180279939
Full Text :
https://doi.org/10.1002/pra2.1039