{"title":"在大型语言模型（LLM）上训练的人工智能代理对年轻人抑郁和焦虑症状的干预效果：一项为期28天的随机对照试验","authors":"Yuqing Zhao, Wei Qian, Yaru Chen, Donghong Wu, Yujia Luo, Cong Gao, Kankan Wu, Zhengkui Liu","doi":"10.1111/aphw.70067","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Young adults face emotional problems in their daily lives. Considering that youth are prevalent among mobile internet users, it would be helpful if functions that can intervene in young people's depression and anxiety can be designed based on short video apps. Large language model (LLM)-based AI conversational agents based on short video apps may play an important role in intervening in young adults' negative emotions.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>This study is a 28-day randomized controlled trial (RCT) in which 865 participants were randomly assigned to an intervention group or a waiting group, and each user was asked to engage in a total of 28 days of dialog intervention with the AI agent and complete three psychological questionnaires.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The dialog intervention significantly reduced depression in the intervention group at two weeks and significantly reduced both depression and anxiety in the intervention group at four weeks.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>This study found evidence that the LLM-based conversational agent could effectively alleviate the mild anxiety and depressive symptoms of young adults with negative emotions through dialog interventions when the AI companion bot is used sufficiently enough.</p>\n </section>\n \n <section>\n \n <h3> Registration</h3>\n \n <p>Clinicaltrials.gov NCT06346496, https://clinicaltrials.gov/study/NCT06346496.</p>\n </section>\n </div>","PeriodicalId":8127,"journal":{"name":"Applied psychology. Health and well-being","volume":"17 5","pages":""},"PeriodicalIF":3.6000,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Effect of an AI agent trained on a large language model (LLM) as an intervention for depression and anxiety symptoms in young adults: A 28-day randomized controlled trial\",\"authors\":\"Yuqing Zhao, Wei Qian, Yaru Chen, Donghong Wu, Yujia Luo, Cong Gao, Kankan Wu, Zhengkui Liu\",\"doi\":\"10.1111/aphw.70067\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n \\n <section>\\n \\n <h3> Background</h3>\\n \\n <p>Young adults face emotional problems in their daily lives. Considering that youth are prevalent among mobile internet users, it would be helpful if functions that can intervene in young people's depression and anxiety can be designed based on short video apps. Large language model (LLM)-based AI conversational agents based on short video apps may play an important role in intervening in young adults' negative emotions.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Methods</h3>\\n \\n <p>This study is a 28-day randomized controlled trial (RCT) in which 865 participants were randomly assigned to an intervention group or a waiting group, and each user was asked to engage in a total of 28 days of dialog intervention with the AI agent and complete three psychological questionnaires.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Results</h3>\\n \\n <p>The dialog intervention significantly reduced depression in the intervention group at two weeks and significantly reduced both depression and anxiety in the intervention group at four weeks.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Conclusions</h3>\\n \\n <p>This study found evidence that the LLM-based conversational agent could effectively alleviate the mild anxiety and depressive symptoms of young adults with negative emotions through dialog interventions when the AI companion bot is used sufficiently enough.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Registration</h3>\\n \\n <p>Clinicaltrials.gov NCT06346496, https://clinicaltrials.gov/study/NCT06346496.</p>\\n </section>\\n </div>\",\"PeriodicalId\":8127,\"journal\":{\"name\":\"Applied psychology. Health and well-being\",\"volume\":\"17 5\",\"pages\":\"\"},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2025-09-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Applied psychology. Health and well-being\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://iaap-journals.onlinelibrary.wiley.com/doi/10.1111/aphw.70067\",\"RegionNum\":2,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PSYCHOLOGY, APPLIED\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied psychology. Health and well-being","FirstCategoryId":"102","ListUrlMain":"https://iaap-journals.onlinelibrary.wiley.com/doi/10.1111/aphw.70067","RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHOLOGY, APPLIED","Score":null,"Total":0}
引用次数: 0
摘要
年轻人在日常生活中面临着情感问题。考虑到年轻人在移动互联网用户中普遍存在，如果能够基于短视频应用设计出能够干预年轻人抑郁和焦虑的功能，将会很有帮助。基于大语言模型（Large language model， LLM）的基于短视频应用的人工智能会话代理可能在干预青少年负面情绪方面发挥重要作用。方法采用28天的随机对照试验（RCT），将865名参与者随机分为干预组和等待组，要求每位用户与AI智能体进行为期28天的对话干预，并完成3份心理问卷。结果对话干预在第2周显著降低了干预组的抑郁情绪，在第4周显著降低了干预组的抑郁和焦虑情绪。本研究发现有证据表明，在充分使用AI伴侣机器人的情况下，基于llm的对话代理可以通过对话干预有效缓解具有负面情绪的年轻人的轻度焦虑和抑郁症状。注册Clinicaltrials.gov NCT06346496, https://clinicaltrials.gov/study/NCT06346496。
Effect of an AI agent trained on a large language model (LLM) as an intervention for depression and anxiety symptoms in young adults: A 28-day randomized controlled trial
Background
Young adults face emotional problems in their daily lives. Considering that youth are prevalent among mobile internet users, it would be helpful if functions that can intervene in young people's depression and anxiety can be designed based on short video apps. Large language model (LLM)-based AI conversational agents based on short video apps may play an important role in intervening in young adults' negative emotions.
Methods
This study is a 28-day randomized controlled trial (RCT) in which 865 participants were randomly assigned to an intervention group or a waiting group, and each user was asked to engage in a total of 28 days of dialog intervention with the AI agent and complete three psychological questionnaires.
Results
The dialog intervention significantly reduced depression in the intervention group at two weeks and significantly reduced both depression and anxiety in the intervention group at four weeks.
Conclusions
This study found evidence that the LLM-based conversational agent could effectively alleviate the mild anxiety and depressive symptoms of young adults with negative emotions through dialog interventions when the AI companion bot is used sufficiently enough.
期刊介绍：
Applied Psychology: Health and Well-Being is a triannual peer-reviewed academic journal published by Wiley-Blackwell on behalf of the International Association of Applied Psychology. It was established in 2009 and covers applied psychology topics such as clinical psychology, counseling, cross-cultural psychology, and environmental psychology.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
