ChatGPT如何处理参考查询?基于问题类型和问题复杂性的分析

IF 1.4 3区管理学 Q2 INFORMATION SCIENCE & LIBRARY SCIENCE

College & Research Libraries Pub Date : 2023-01-01 DOI:10.5860/crl.84.6.974

Katie Lai

{"title":"ChatGPT如何处理参考查询?基于问题类型和问题复杂性的分析","authors":"Katie Lai","doi":"10.5860/crl.84.6.974","DOIUrl":null,"url":null,"abstract":"To explore whether artificial intelligence can be used to enhance library services, this study used ChatGPT to answer reference questions. An assessment rubric was used to evaluate how well ChatGPT handled different question types and difficulty levels. Overall ChatGPT’s performance was fair, but it did poorly in information accuracy. It scored the highest when handling facilities and equipment-related questions but the lowest when dealing with e-resources access problems. ChatGPT was weak in answering advanced research questions, complex inquiries, and known item searches relating to a specific local environment, but it could be adopted to enhance library communication with users.","PeriodicalId":10686,"journal":{"name":"College & Research Libraries","volume":"1 1","pages":"0"},"PeriodicalIF":1.4000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"How Well Does ChatGPT Handle Reference Inquiries? An Analysis Based on Question Types and Question Complexities\",\"authors\":\"Katie Lai\",\"doi\":\"10.5860/crl.84.6.974\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"To explore whether artificial intelligence can be used to enhance library services, this study used ChatGPT to answer reference questions. An assessment rubric was used to evaluate how well ChatGPT handled different question types and difficulty levels. Overall ChatGPT’s performance was fair, but it did poorly in information accuracy. It scored the highest when handling facilities and equipment-related questions but the lowest when dealing with e-resources access problems. ChatGPT was weak in answering advanced research questions, complex inquiries, and known item searches relating to a specific local environment, but it could be adopted to enhance library communication with users.\",\"PeriodicalId\":10686,\"journal\":{\"name\":\"College & Research Libraries\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"College & Research Libraries\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5860/crl.84.6.974\",\"RegionNum\":3,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"INFORMATION SCIENCE & LIBRARY SCIENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"College & Research Libraries","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5860/crl.84.6.974","RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"INFORMATION SCIENCE & LIBRARY SCIENCE","Score":null,"Total":0}

引用次数: 0

摘要

为了探讨人工智能是否可以用来增强图书馆服务，本研究使用ChatGPT来回答参考问题。一个评估标准被用来评估ChatGPT如何很好地处理不同的问题类型和难度水平。总体而言，ChatGPT的表现尚可，但在信息准确性方面表现不佳。它在处理设施和设备相关问题时得分最高，但在处理电子资源访问问题时得分最低。ChatGPT在回答高级研究问题、复杂查询和与特定本地环境相关的已知项目搜索方面较弱，但它可以用于加强图书馆与用户的沟通。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

How Well Does ChatGPT Handle Reference Inquiries? An Analysis Based on Question Types and Question Complexities

To explore whether artificial intelligence can be used to enhance library services, this study used ChatGPT to answer reference questions. An assessment rubric was used to evaluate how well ChatGPT handled different question types and difficulty levels. Overall ChatGPT’s performance was fair, but it did poorly in information accuracy. It scored the highest when handling facilities and equipment-related questions but the lowest when dealing with e-resources access problems. ChatGPT was weak in answering advanced research questions, complex inquiries, and known item searches relating to a specific local environment, but it could be adopted to enhance library communication with users.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

College & Research Libraries INFORMATION SCIENCE & LIBRARY SCIENCE-

CiteScore

3.10

自引率

22.20%

发文量

审稿时长

45 weeks

期刊介绍： College & Research Libraries (C&RL) is the official scholarly research journal of the Association of College & Research Libraries, a division of the American Library Association, 50 East Huron St., Chicago, IL 60611. C&RL is a bimonthly, online-only publication highlighting a new C&RL study with a free, live, expert panel comprised of the study''s authors and additional subject experts.