关系咨询中的人工智能:评估 ChatGPT 在提供恋爱咨询方面的治疗能力

Laura M. Vowels , Rachel R.R. Francois-Walcott , Joëlle Darwiche
{"title":"关系咨询中的人工智能:评估 ChatGPT 在提供恋爱咨询方面的治疗能力","authors":"Laura M. Vowels ,&nbsp;Rachel R.R. Francois-Walcott ,&nbsp;Joëlle Darwiche","doi":"10.1016/j.chbah.2024.100078","DOIUrl":null,"url":null,"abstract":"<div><p>Recent advancements in AI have led to chatbots, such as ChatGPT, capable of providing therapeutic responses. Early research evaluating chatbots' ability to provide relationship advice and single-session relationship interventions has showed that both laypeople and relationship therapists rate them high on attributed such as empathy and helpfulness. In the present study, 20 participants engaged in single-session relationship intervention with ChatGPT and were interviewed about their experiences. We evaluated the performance of ChatGPT comprising of technical outcomes such as error rate and linguistic accuracy and therapeutic quality such as empathy and therapeutic questioning. The interviews were analysed using reflexive thematic analysis which generated four themes: light at the end of the tunnel; clearing the fog; clinical skills; and therapeutic setting. The analyses of technical and feasibility outcomes, as coded by researchers and perceived by users, show ChatGPT provides realistic single-session intervention with it consistently rated highly on attributes such as therapeutic skills, human-likeness, exploration, and useability, and providing clarity and next steps for users’ relationship problem. Limitations include a poor assessment of risk and reaching collaborative solutions with the participant. This study extends on AI acceptance theories and highlights the potential capabilities of ChatGPT in providing relationship advice and support.</p></div>","PeriodicalId":100324,"journal":{"name":"Computers in Human Behavior: Artificial Humans","volume":"2 2","pages":"Article 100078"},"PeriodicalIF":0.0000,"publicationDate":"2024-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949882124000380/pdfft?md5=d4b9aa843c4d16b685ded5378e52197c&pid=1-s2.0-S2949882124000380-main.pdf","citationCount":"0","resultStr":"{\"title\":\"AI in relationship counselling: Evaluating ChatGPT's therapeutic capabilities in providing relationship advice\",\"authors\":\"Laura M. Vowels ,&nbsp;Rachel R.R. Francois-Walcott ,&nbsp;Joëlle Darwiche\",\"doi\":\"10.1016/j.chbah.2024.100078\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Recent advancements in AI have led to chatbots, such as ChatGPT, capable of providing therapeutic responses. Early research evaluating chatbots' ability to provide relationship advice and single-session relationship interventions has showed that both laypeople and relationship therapists rate them high on attributed such as empathy and helpfulness. In the present study, 20 participants engaged in single-session relationship intervention with ChatGPT and were interviewed about their experiences. We evaluated the performance of ChatGPT comprising of technical outcomes such as error rate and linguistic accuracy and therapeutic quality such as empathy and therapeutic questioning. The interviews were analysed using reflexive thematic analysis which generated four themes: light at the end of the tunnel; clearing the fog; clinical skills; and therapeutic setting. The analyses of technical and feasibility outcomes, as coded by researchers and perceived by users, show ChatGPT provides realistic single-session intervention with it consistently rated highly on attributes such as therapeutic skills, human-likeness, exploration, and useability, and providing clarity and next steps for users’ relationship problem. Limitations include a poor assessment of risk and reaching collaborative solutions with the participant. This study extends on AI acceptance theories and highlights the potential capabilities of ChatGPT in providing relationship advice and support.</p></div>\",\"PeriodicalId\":100324,\"journal\":{\"name\":\"Computers in Human Behavior: Artificial Humans\",\"volume\":\"2 2\",\"pages\":\"Article 100078\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-06-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2949882124000380/pdfft?md5=d4b9aa843c4d16b685ded5378e52197c&pid=1-s2.0-S2949882124000380-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computers in Human Behavior: Artificial Humans\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2949882124000380\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers in Human Behavior: Artificial Humans","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2949882124000380","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

最近,人工智能的进步促使聊天机器人(如 ChatGPT)能够提供治疗回复。对聊天机器人提供恋爱建议和单次恋爱干预能力的早期评估研究表明,无论是普通人还是恋爱治疗师,都对聊天机器人的同理心和帮助性给予了很高的评价。在本研究中,20 名参与者使用 ChatGPT 进行了单次关系干预,并就他们的体验接受了采访。我们对 ChatGPT 的性能进行了评估,包括错误率和语言准确性等技术成果以及移情和治疗性提问等治疗质量。我们采用反思性主题分析法对访谈进行了分析,得出了四个主题:隧道尽头的曙光;拨开迷雾;临床技能;治疗环境。根据研究人员的编码和用户的感知,对技术和可行性结果的分析表明,ChatGPT 提供了现实的单次会话干预,在治疗技能、人性化、探索性和可用性等属性上始终获得很高的评价,并为用户的关系问题提供了清晰的思路和下一步措施。其局限性包括对风险的评估不足,以及无法与参与者达成合作解决方案。本研究扩展了人工智能接受理论,并强调了 ChatGPT 在提供关系建议和支持方面的潜在能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
AI in relationship counselling: Evaluating ChatGPT's therapeutic capabilities in providing relationship advice

Recent advancements in AI have led to chatbots, such as ChatGPT, capable of providing therapeutic responses. Early research evaluating chatbots' ability to provide relationship advice and single-session relationship interventions has showed that both laypeople and relationship therapists rate them high on attributed such as empathy and helpfulness. In the present study, 20 participants engaged in single-session relationship intervention with ChatGPT and were interviewed about their experiences. We evaluated the performance of ChatGPT comprising of technical outcomes such as error rate and linguistic accuracy and therapeutic quality such as empathy and therapeutic questioning. The interviews were analysed using reflexive thematic analysis which generated four themes: light at the end of the tunnel; clearing the fog; clinical skills; and therapeutic setting. The analyses of technical and feasibility outcomes, as coded by researchers and perceived by users, show ChatGPT provides realistic single-session intervention with it consistently rated highly on attributes such as therapeutic skills, human-likeness, exploration, and useability, and providing clarity and next steps for users’ relationship problem. Limitations include a poor assessment of risk and reaching collaborative solutions with the participant. This study extends on AI acceptance theories and highlights the potential capabilities of ChatGPT in providing relationship advice and support.

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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信