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

TL;DR

This paper explores using ChatGPT to generate Library of Congress Subject Headings for electronic theses and dissertations, aiming to streamline cataloging and improve resource discoverability, while emphasizing the need for human verification.

Contribution

It demonstrates the potential of ChatGPT to assist in LCSH assignment for ETDs, highlighting both benefits and the necessity of human oversight.

Findings

LLMs can reduce cataloging time.

ChatGPT improves resource discoverability.

Human verification remains essential.

Abstract

This study delves into the potential use of large language models (LLMs) for generating Library of Congress Subject Headings (LCSH). The authors employed ChatGPT to generate subject headings for electronic theses and dissertations (ETDs) based on their titles and abstracts. The results suggests that LLMs such as ChatGPT have the potential to reduce cataloging time needed for assigning LCSH subject terms 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 LCSH generated by LLMs.