Cover Image

AI Chatbots and Subject Cataloging: A Performance Test

Saved in:
Published in:Library Resources & Technical Services vol. 69, no. 2 (Apr 2025)
Main Author: Dobreski, Brian
Other Authors: Hastings, Christopher
Published:
American Library Association
Subjects:
Classification
Artificial intelligence
Chatbots
Performance tests
Effectiveness
Libraries
Human-computer interaction
Cataloging
Errors
Researcher subject relations
Task performance
Legislatures
Text structure
Online Access:Citation/Abstract
Full Text - PDF
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract:Libraries show an increasing interest in incorporating AI tools into their workflows, particularlyeasily accessible and free-to-use chatbots. However, empirical evidence is limited regarding theeffectiveness of these tools to perform traditionally time-consuming subject cataloging tasks. In thisstudy, researchers sought to assess the performance of AI tools in performing basic subject headingand classification number assignment. Using a well-established instructional cataloging text as abasis, researchers developed and administered a test designed to evaluate the effectiveness of three chatbots (ChatGPT, Gemini, Copilot) in assigning Dewey Decimal Classification, Library of Congress Classification, and Library of Congress Subject Heading terms and numbers. The quantity and quality of errors in chatbot responses were analyzed.
ISSN:0024-2527
2159-9610
DOI:10.5860/lrts.69n2.8440
Source:Library Science Database