{"title":"使用生成式人工智能开发和改进人格量表：使用ChatGPT 4.0开发的短HEXACO量表的心理测量特性。","authors":"Ard J Barends, Reinout E de Vries","doi":"10.1080/00223891.2024.2444454","DOIUrl":null,"url":null,"abstract":"<p><p>In the current study, we investigated the utility of generative AI for survey development and improvement. To do so, we generated a 24-item HEXACO personality inventory using ChatGPT 4.0, the ChatGPT HEXACO inventory (CHI), and investigated whether ChatGPT could modify the CHI to either improve its internal consistency or its content validity. Additionally, we compared the psychometric properties of the different versions of the CHI to a conceptually similar short personality inventory. Specifically, we compared the three CHI versions with the Brief HEXACO inventory (BHI) in terms of their alpha reliabilities and their convergent and discriminant correlations with the HEXACO-60 and criterion-related validity with authoritarianism and social dominance orientation. Participants <i>(N</i> = 682) completed the BHI and HEXACO-60 and were randomly assigned to complete one of the three CHI versions. The results showed generally comparable psychometric properties of the three CHI versions and the BHI. However, ChatGPT could not improve specific psychometric properties of the CHI. That is, although the results show promise for the use of ChatGPT in developing questionnaires, it may not offer a shortcut to further improve specific psychometric properties.</p>","PeriodicalId":16707,"journal":{"name":"Journal of personality assessment","volume":" ","pages":"1-7"},"PeriodicalIF":2.8000,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Developing and Improving Personality Inventories Using Generative Artificial Intelligence: The Psychometric Properties of a Short HEXACO Scale Developed Using ChatGPT 4.0.\",\"authors\":\"Ard J Barends, Reinout E de Vries\",\"doi\":\"10.1080/00223891.2024.2444454\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>In the current study, we investigated the utility of generative AI for survey development and improvement. To do so, we generated a 24-item HEXACO personality inventory using ChatGPT 4.0, the ChatGPT HEXACO inventory (CHI), and investigated whether ChatGPT could modify the CHI to either improve its internal consistency or its content validity. Additionally, we compared the psychometric properties of the different versions of the CHI to a conceptually similar short personality inventory. Specifically, we compared the three CHI versions with the Brief HEXACO inventory (BHI) in terms of their alpha reliabilities and their convergent and discriminant correlations with the HEXACO-60 and criterion-related validity with authoritarianism and social dominance orientation. Participants <i>(N</i> = 682) completed the BHI and HEXACO-60 and were randomly assigned to complete one of the three CHI versions. The results showed generally comparable psychometric properties of the three CHI versions and the BHI. However, ChatGPT could not improve specific psychometric properties of the CHI. That is, although the results show promise for the use of ChatGPT in developing questionnaires, it may not offer a shortcut to further improve specific psychometric properties.</p>\",\"PeriodicalId\":16707,\"journal\":{\"name\":\"Journal of personality assessment\",\"volume\":\" \",\"pages\":\"1-7\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2024-12-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of personality assessment\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://doi.org/10.1080/00223891.2024.2444454\",\"RegionNum\":3,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"PSYCHOLOGY, CLINICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of personality assessment","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1080/00223891.2024.2444454","RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PSYCHOLOGY, CLINICAL","Score":null,"Total":0}
Developing and Improving Personality Inventories Using Generative Artificial Intelligence: The Psychometric Properties of a Short HEXACO Scale Developed Using ChatGPT 4.0.
In the current study, we investigated the utility of generative AI for survey development and improvement. To do so, we generated a 24-item HEXACO personality inventory using ChatGPT 4.0, the ChatGPT HEXACO inventory (CHI), and investigated whether ChatGPT could modify the CHI to either improve its internal consistency or its content validity. Additionally, we compared the psychometric properties of the different versions of the CHI to a conceptually similar short personality inventory. Specifically, we compared the three CHI versions with the Brief HEXACO inventory (BHI) in terms of their alpha reliabilities and their convergent and discriminant correlations with the HEXACO-60 and criterion-related validity with authoritarianism and social dominance orientation. Participants (N = 682) completed the BHI and HEXACO-60 and were randomly assigned to complete one of the three CHI versions. The results showed generally comparable psychometric properties of the three CHI versions and the BHI. However, ChatGPT could not improve specific psychometric properties of the CHI. That is, although the results show promise for the use of ChatGPT in developing questionnaires, it may not offer a shortcut to further improve specific psychometric properties.
期刊介绍：
The Journal of Personality Assessment (JPA) primarily publishes articles dealing with the development, evaluation, refinement, and application of personality assessment methods. Desirable articles address empirical, theoretical, instructional, or professional aspects of using psychological tests, interview data, or the applied clinical assessment process. They also advance the measurement, description, or understanding of personality, psychopathology, and human behavior. JPA is broadly concerned with developing and using personality assessment methods in clinical, counseling, forensic, and health psychology settings; with the assessment process in applied clinical practice; with the assessment of people of all ages and cultures; and with both normal and abnormal personality functioning.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
