PsyGUARD: An Automated System for Suicide Detection and Risk Assessment in Psychological Counseling
Abstract: As awareness of mental health crises grows, online emergency support services are becoming increasingly prevalent worldwide. Detecting whether users express suicidal ideation in text-based counseling services is crucial to identify and prioritize at-risk individuals. However, the lack of domain-specific models for enhancing fine-grained suicide prevention in online counseling poses a significant challenge for the automated detection and intervention of suicide risk. In this paper, we propose PsyGUARD, an automated system for suicide detection and risk assessment in psychological counseling. We first develop a fine-grained taxonomy for suicide detection based on numerous theories. We then build a large-scale, high-quality, and fine-grained suicide risk detection dataset called PsyGUARD. To understand the capabilities of automated systems in suicide risk detection, we establish various benchmarks. To assist automated services in providing safe, helpful, and personalized responses during risk assessment, we propose building a risk assessment system for clients during online text-based counseling. Our work provides an insightful analysis of the effectiveness of automated risk assessment systems and their potential impact on improving mental health services in online counseling platforms.
Paper Type: Long
Research Area: Sentiment Analysis, Stylistic Analysis, and Argument Mining
Research Area Keywords: automated system, suicide detection, risk assessment, psychological counseling
Contribution Types: Model analysis & interpretability, Publicly available software and/or pre-trained models, Data resources, Data analysis
Languages Studied: Chinese
Submission Number: 824
Loading