DAIC-WOZ: On the Validity of Using the Therapist's prompts in Automatic Depression Detection from Clinical Interviews
Idiap Research Institute(伊迪亚普研究所);Mathematics Research Center (CIMAT)(数学研究中心(CIMAT));Consejo Nacional de Humanidades, Ciencias y Tecnologías (CONAHCYT)(国家人文科学与技术委员会(CONAHCYT));Brno University of Technology(布尔诺理工大学)
Sergio Burdisso, Ernesto Reyes-Ramírez, Esaú Villatoro-Tello, Fernando Sánchez-Vega, Pastor López-Monroy, Petr Motlicek
Automatic depression detection from conversational data has gained significant interest in recent years. The DAIC-WOZ dataset, interviews conducted by a human-controlled virtual agent, has been widely used for this task. Recent studies have reported enhanced performance when incorporating interviewer's prompts into the model. In this work, we hypothesize that this improvement might be mainly due to a bias present in these prompts, rather than the proposed architectures and methods. Through ablation experiments and qualitative analysis, we discover that models using interviewer's prompts learn to focus on a specific region of the interviews, where questions about past experiences with mental health issues are asked, and use them as discriminative shortcuts to detect depressed participants. In contrast, models using participant responses gather evidence from across the entire interview. Finally, to highlight the magnitude of this bias, we achieve a 0.90 F1 score by intentionally exploiting it, the highest result reported to date on this dataset using only textual information. Our findings underline the need for caution when incorporating interviewers' prompts into models, as they may inadvertently learn to exploit targeted prompts, rather than learning to characterize the language and behavior that are genuinely indicative of the patient's mental health condition.
Probabilistic Textual Time Series Depression Detection
Department of Computer Science, KTH Royal Institute of Technology(计算机科学系,皇家理工学院);Department of Information Technology, Uppsala University(信息科技系,乌普萨拉大学)
Psychologically-Grounded Graph Modeling for Interpretable Depression Detection
Singapore Institute of Technology(新加坡科技学院);Nanyang Technological University(南洋理工大学);ELLIS Institute Finland(芬兰ELLIS研究所);University of Turku(图尔库大学);Princess Nourah bint Abdulrahman University(普里西拉努拉·本·阿卜杜勒拉赫曼大学)
Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM Reasoning
School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Guangdong, China(哈尔滨工业大学(深圳)计算机科学与技术学院);School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China(江南大学人工智能与计算机学院);Guangdong Provincial Key Laboratory of Intelligent Information Processing(广东省智能信息处理重点实验室);Pengcheng Laboratory(鹏城实验室);Chinese People’s Liberation Army General Hospital, Beijing, China(中国人民解放军总医院)
DepFlow: Disentangled Speech Generation to Mitigate Semantic Bias in Depression Detection
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院);School of Electrical Engineering and Telecommunications, UNSW(新南威尔士大学电信工程学院);School of Software and Microelectronics, Peking University(北京大学软件与微电子学院);Center for AI in Medicine (C-AIM), Lee Kong Chian School of Medicine, NTU(人工智能医学中心(C-AIM)、李光耀医学院、南洋理工大学)
Assessing Algorithmic Bias in Language-Based Depression Detection: A Comparison of DNN and LLM Approaches
Computer Science University of Colorado Boulder Boulder, CO, USA;Inst. Cognitive Science \& Computer Science University of Colorado Boulder Boulder, CO, USA