An Experiment with the Use of ChatGPT for LCSH Subject Assignment on Electronic Theses and Dissertations

• Published in: Cataloging & classification quarterly Vol. 62; no. 5; pp. 574 - 588
• Main Authors: Chow, Eric H. C., Kao, T. J., Li, Xiaoli
• Format: Journal Article
• Language: English
• Published: New York Routledge 03.07.2024; Taylor & Francis Ltd
• Subjects: Academic libraries; Chatbots; electronic theses and dissertations (ETDs); Large language models; Library of Congress Subject Headings; Library of Congress Subject Headings (LCSH); subject analysis
• ISSN: 0163-9374; 1544-4554
• DOI: 10.1080/01639374.2024.2394516

This study delves into the potential use of large language models (LLMs) for generating Library of Congress subject headings. The authors employed ChatGPT to generate subject headings for electronic theses and dissertations (ETDs) based on their titles and abstracts. The results suggest that LLMs such as ChatGPT have the potential to reduce the cataloging time needed for assigning subject terms from Library of Congress Subject Headings (LCSH) for ETDs as well as to improve the discovery of this type of resource in academic libraries. Nonetheless, human catalogers remain essential for verifying and enhancing the validity, exhaustivity, and specificity of Library of Congress subject headings generated by LLMs.