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

Eric H. C. Chow*, T. J. Kao, Xiaoli Li

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

Abstract

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.
Original languageEnglish
Pages (from-to)574-588
Number of pages15
JournalCataloging and Classification Quarterly
Volume62
Issue number5
DOIs
Publication statusPublished - Sept 2024

Scopus Subject Areas

  • Library and Information Sciences

User-Defined Keywords

  • Large language models
  • Library of Congress Subject Headings (LCSH)
  • electronic theses and dissertations (ETDs)
  • subject analysis

Fingerprint

Dive into the research topics of 'An Experiment with the Use of ChatGPT for LCSH Subject Assignment on Electronic Theses and Dissertations'. Together they form a unique fingerprint.

Cite this