{"title":"ChatGPTest: Opportunities and Cautionary Tales of Utilizing AI for Questionnaire Pretesting","authors":"Francisco Olivos, Minhui Liu","doi":"10.1177/1525822x241280574","DOIUrl":null,"url":null,"abstract":"The rapid advancements in generative artificial intelligence have opened new avenues for enhancing various aspects of research, including the design and evaluation of survey questionnaires. However, the recent pioneering applications have not considered questionnaire pretesting. This article explores the use of GPT models as a useful tool for pretesting survey questionnaires, particularly in the early stages of survey design. Illustrated with two applications, the article suggests incorporating GPT feedback as an additional stage before human pretesting, potentially reducing successive iterations. The article also emphasizes the indispensable role of researchers’ judgment in interpreting and implementing AI-generated feedback.","PeriodicalId":48060,"journal":{"name":"Field Methods","volume":null,"pages":null},"PeriodicalIF":1.1000,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Field Methods","FirstCategoryId":"90","ListUrlMain":"https://doi.org/10.1177/1525822x241280574","RegionNum":3,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ANTHROPOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
The rapid advancements in generative artificial intelligence have opened new avenues for enhancing various aspects of research, including the design and evaluation of survey questionnaires. However, the recent pioneering applications have not considered questionnaire pretesting. This article explores the use of GPT models as a useful tool for pretesting survey questionnaires, particularly in the early stages of survey design. Illustrated with two applications, the article suggests incorporating GPT feedback as an additional stage before human pretesting, potentially reducing successive iterations. The article also emphasizes the indispensable role of researchers’ judgment in interpreting and implementing AI-generated feedback.
期刊介绍：
Field Methods (formerly Cultural Anthropology Methods) is devoted to articles about the methods used by field wzorkers in the social and behavioral sciences and humanities for the collection, management, and analysis data about human thought and/or human behavior in the natural world. Articles should focus on innovations and issues in the methods used, rather than on the reporting of research or theoretical/epistemological questions about research. High-quality articles using qualitative and quantitative methods-- from scientific or interpretative traditions-- dealing with data collection and analysis in applied and scholarly research from writers in the social sciences, humanities, and related professions are all welcome in the pages of the journal.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
