AI Chatbots and Subject Cataloging: A Performance Test
Abstract
Libraries show an increasing interest in incorporating AI tools into their workflows, particularly
easily accessible and free-to-use chatbots. However, empirical evidence is limited regarding the
effectiveness of these tools to perform traditionally time-consuming subject cataloging tasks. In this
study, researchers sought to assess the performance of AI tools in performing basic subject heading
and classification number assignment. Using a well-established instructional cataloging text as a
basis, 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.
easily accessible and free-to-use chatbots. However, empirical evidence is limited regarding the
effectiveness of these tools to perform traditionally time-consuming subject cataloging tasks. In this
study, researchers sought to assess the performance of AI tools in performing basic subject heading
and classification number assignment. Using a well-established instructional cataloging text as a
basis, 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.
Full Text:
PDFDOI: https://doi.org/10.5860/lrts.69n2.8440
Refbacks
- There are currently no refbacks.
Copyright (c) 2025 Brian Dobreski, Christopher Hastings
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.