바로가기메뉴

본문 바로가기 주메뉴 바로가기

logo

ISSN : 1013-0799

Article Contents

Prev Next
e-Submission

Vol.41 No.3

Citation Share

ChatGPT-Based Book Recommendation System for Learning Korean in a University Library

Journal of the Korean Society for Information Management / Journal of the Korean Society for Information Management, (P)1013-0799; (E)2586-2073
2024, v.41 no.3, pp.145-169
https://doi.org/10.3743/KOSIM.2024.41.3.145
Jung Im Yun (Daegu Catholic University)
Sanghee Choi (Daegu Catholic University)
Yun, J. I., & Choi, S. (2024). ChatGPT-Based Book Recommendation System for Learning Korean in a University Library. Journal of the Korean Society for Information Management, 41(3), 145-169, https://doi.org/10.3743/KOSIM.2024.41.3.145

Abstract

This study examined university library services for students, including international students, and the AI-based information services provided by libraries. Additionally, the standards of Korean language education for international students were investigated. Based on the analysis of library services and these standards, a book recommendation system for learning Korean was developed using ChatGPT. The recommendation results from three training datasets were evaluated for recommendation precision. The results of the chatbot’s book recommendations based on the 13 test questions were evaluated by recommendation precision. The comparison of the recommendation precision showed that the chatbot using the combined dataset was more successful in recommending all relevant books compared to the individual datasets. This study serves as an example of an effective approach to utilizing artificial intelligence technology for user services in university libraries.

keywords
university library, foreign students, library service, chatbot, ChatGPT, book recommendation, Korean learning
Submission Date
2024-08-15
Revised Date
2024-08-27
Accepted Date
2024-09-01

Journal of the Korean Society for Information Management

e-Submission OA Policy