We Care：多模态抑郁检测与知识注入的心理健康治疗响应生成
We Care: Multimodal Depression Detection and Knowledge Infused Mental Health Therapeutic Response Generation
AI总结：
本文提出Extended D-vlog多模态数据集和基于CBT的虚拟代理，结合Mistral与TVLT模型实现抑郁检测与治疗响应生成，缓解LLM在现实心理健康应用中的风险。
摘要：
通过非言语线索检测抑郁已获得显著关注。以往研究主要集中在受控实验室环境中识别抑郁，通常需要心理学家或咨询师的监督。不幸的是，在这种受控环境中生成的数据集可能难以解释个体在现实生活情境中的行为。针对这一局限，我们提出了Extended D-vlog数据集，该数据集包含1,261个YouTube视频博客。此外，GPT3.5和GPT4等大型语言模型（LLMs）的出现引发了人们对其能否像心理健康专业人士一样发挥作用的兴趣。然而，这些LLM模型在现实环境中使用的就绪性仍然令人担忧，因为它们可能给出错误的回应，从而伤害用户。我们引入了一个虚拟代理，作为心理健康患者的初始接触点，提供基于认知行为疗法（CBT）的回应。它包含两个核心功能：1. 识别个体的抑郁状况；2. 提供基于CBT的治疗性回应。我们的Mistral模型在失真评估和分类上分别取得了70.1%和30.9%的显著分数，Bert分数为88.7%。此外，在我们的多模态Extended D-vlog数据集上使用TVLT模型取得了优异结果，F1分数达到67.8%。
英文摘要：
The detection of depression through non-verbal cues has gained significant attention. Previous research predominantly centred on identifying depression within the confines of controlled laboratory environments, often with the supervision of psychologists or counsellors. Unfortunately, datasets generated in such controlled settings may struggle to account for individual behaviours in real-life situations. In response to this limitation, we present the Extended D-vlog dataset, encompassing a collection of 1, 261 YouTube vlogs. Additionally, the emergence of large language models (LLMs) like GPT3.5, and GPT4 has sparked interest in their potential they can act like mental health professionals. Yet, the readiness of these LLM models to be used in real-life settings is still a concern as they can give wrong responses that can harm the users. We introduce a virtual agent serving as an initial contact for mental health patients, offering Cognitive Behavioral Therapy (CBT)-based responses. It comprises two core functions: 1. Identifying depression in individuals, and 2. Delivering CBT-based therapeutic responses. Our Mistral model achieved impressive scores of 70.1% and 30.9% for distortion assessment and classification, along with a Bert score of 88.7%. Moreover, utilizing the TVLT model on our Multimodal Extended D-vlog Dataset yielded outstanding results, with an impressive F1-score of 67.8%
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
