喻园管理论坛2024年第99期(总第1031期)

演讲主题:Digital Technology-Based Health Status Recognition Method for Mental Illness Patients

主讲人:邝俊伟 北京理工大学博士

主持人:杨彦武 信息管理与数据科学系主任

活动时间:2024年11月21日（周四）14：30-16：30

活动地点:管院大楼406室

主讲人简介：

邝俊伟，北京理工大学管理科学与工程系博士研究生，研究方向包括数字健康管理、设计科学、社交媒体分析和深度学习等领域。他的研究成果曾发表于ICIS 和 HICSS 等信息系统领域的国际顶尖会议。此外，他还担任 2024 年 INFORMS 数据科学研讨会组委会成员，并为 ICIS、PACIS、HICSS 以及《Online Information Review》等多项会议和期刊提供审稿服务。

活动简介：

Depression is a common mental disorder involving a depressed mood or loss of pleasure for long periods, which induces grave financial and societal ramifications. Social media-based depression detection is an effective method for early intervention to mitigate those consequences. Such a high-stake decision inherently necessitates interpretability. Although a few studies explain this decision based on the importance of linguistic or demographic features, these explanations do not directly relate to depression diagnosis criteria that are based on symptoms. To fill this gap, we develop a Focused Temporal Prototype Network (FTPNet) to detect depression and provide interpretations based on depressive symptoms as well as their temporal distributions. Extensive evaluations using large-scale datasets show that FTPNet outperforms comprehensive benchmark methods with an F1-score of 0.864. Our result also reveals new symptoms, such as sharing admiration for a different life, that are unnoted in traditional depression surveys like the Patient Health Questionnaire-9 (PHQ-9). We further conduct a user study to demonstrate improved interpretability over the benchmark. This study contributes to the Information Systems (IS) literature by introducing an interpretable depression detection approach with a novel prototype design. In practice, multiple stakeholders, such as social media platforms and volunteers, can apply our approach to identify depressed users and deliver targeted interventions.