ChatGPT not Useful as a Tool to Streamline Library Cataloguing Processes

IF 0.4 Q4 INFORMATION SCIENCE & LIBRARY SCIENCE Evidence Based Library and Information Practice Pub Date : 2024-06-14 DOI:10.18438/eblip30524

Andrea Miller-Nesbitt

{"title":"ChatGPT not Useful as a Tool to Streamline Library Cataloguing Processes","authors":"Andrea Miller-Nesbitt","doi":"10.18438/eblip30524","DOIUrl":null,"url":null,"abstract":"A Review of:\nBrzustowicz, R. (2023). From ChatGPT to CatGPT: The Implications of Artificial Intelligence on Library Cataloging. Information Technology and Libraries, 42(3). https://doi.org/10.5860/ital.v42i3.16295\nObjective – To evaluate the potential of ChatGPT as a tool for improving efficiency and accuracy in cataloguing library records.\nDesign – Observational, descriptive study.\nSetting – Online, using ChatGPT and the WorldCat catalogue.\nSubject – The Large Language Model (LLM) ChatGPT.\nMethods – Prompting ChatGPT to create MARC records for items in different formats and languages and comparing the ChatGPT derived records versus those obtained from the WorldCat catalogue.\nMain results – ChatGPT was able to generate MARC records, but the accuracy of the records was questionable, despite the authors’ claims.\nConclusion – Based on the results of this study, the author concludes that using ChatGPT to streamline the process of cataloging could allow library staff to focus time and energy on other types of work. However, the results presented suggest that ChatGPT introduces significant errors in the MARC records created, thereby requiring additional time for cataloguers to correct the error-laden records. The author correctly stresses that if ChatGPT were used to assist with cataloguing, it would remain important for professionals to check the records for completion and accuracy.","PeriodicalId":45227,"journal":{"name":"Evidence Based Library and Information Practice","volume":null,"pages":null},"PeriodicalIF":0.4000,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Evidence Based Library and Information Practice","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18438/eblip30524","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"INFORMATION SCIENCE & LIBRARY SCIENCE","Score":null,"Total":0}

引用次数: 0

Abstract

A Review of: Brzustowicz, R. (2023). From ChatGPT to CatGPT: The Implications of Artificial Intelligence on Library Cataloging. Information Technology and Libraries, 42(3). https://doi.org/10.5860/ital.v42i3.16295 Objective – To evaluate the potential of ChatGPT as a tool for improving efficiency and accuracy in cataloguing library records. Design – Observational, descriptive study. Setting – Online, using ChatGPT and the WorldCat catalogue. Subject – The Large Language Model (LLM) ChatGPT. Methods – Prompting ChatGPT to create MARC records for items in different formats and languages and comparing the ChatGPT derived records versus those obtained from the WorldCat catalogue. Main results – ChatGPT was able to generate MARC records, but the accuracy of the records was questionable, despite the authors’ claims. Conclusion – Based on the results of this study, the author concludes that using ChatGPT to streamline the process of cataloging could allow library staff to focus time and energy on other types of work. However, the results presented suggest that ChatGPT introduces significant errors in the MARC records created, thereby requiring additional time for cataloguers to correct the error-laden records. The author correctly stresses that if ChatGPT were used to assist with cataloguing, it would remain important for professionals to check the records for completion and accuracy.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

ChatGPT 作为简化图书馆编目流程的工具并不实用

Brzustowicz, R. (2023).从 ChatGPT 到 CatGPT：信息技术与图书馆》，42（3）。信息技术与图书馆》，42（3）。https://doi.org/10.5860/ital.v42i3.16295Objective - 评估 ChatGPT 作为提高图书馆记录编目效率和准确性的工具的潜力。设计 - 观察性、描述性研究。设置 - 在线，使用 ChatGPT 和 WorldCat 目录。主题 - 大型语言模型 (LLM) ChatGPT。方法 - 提示 ChatGPT 为不同格式和语言的项目创建 MARC 记录，并将 ChatGPT 生成的记录与从 WorldCat 目录中获得的记录进行比较。主要结果 - ChatGPT 能够生成 MARC 记录，但记录的准确性值得怀疑，尽管作者声称这一点。结论 - 根据这项研究的结果，作者得出结论认为，使用 ChatGPT 简化编目流程可以让图书馆工作人员将时间和精力集中在其他类型的工作上。然而，研究结果表明，ChatGPT 在创建的 MARC 记录中引入了大量错误，因此编目员需要花费更多的时间来纠正错误记录。作者正确地强调，如果使用 ChatGPT 来协助编目，那么专业人员仍然有必要检查记录的完整性和准确性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊