SuiChat-CN: Benchmarking Contextual Suicide Risk Assessment in Chinese Group Chats
This work addresses the underexplored problem of suicide risk assessment in multi-party, fragmented group chats for Chinese-speaking populations, providing a benchmark and insights for mental health research.
The authors introduce SuiChat-CN, a Chinese group-chat benchmark for contextual suicide risk assessment, and show through experiments with over 40 LLMs that contextual information is essential for reliable risk assessment, with fine-tuning and partial-context evaluation revealing challenges in early detection.
Suicide is a critical global public health challenge, causing approximately 720,000 deaths each year and calling for timely, effective prevention strategies. Existing computational studies primarily focus on post-based social media platforms such as Twitter and Weibo, leaving instant messaging environments such as Telegram underexplored. Yet group chats pose distinct challenges: messages are short, fragmented, multi-party, and often rely on implicit or culturally specific expressions, making isolated post-level analysis insufficient. We introduce SuiChat-CN, a Chinese group-chat benchmark for contextual suicide risk assessment. We collect public Telegram group-chat data, construct coherent conversational segments through signal-word extraction and bidirectional context expansion, and annotate user risk levels with an expert-validated, LLM-assisted paradigm. SuiChat-CN contains 13,312 contextual segments from 1,406 users, covering 258,228 raw chat messages. Extensive experiments with PLMs and more than 40 LLMs demonstrate that contextual information is essential for reliable risk assessment, while fine-tuning and partial-context evaluation further reveal the challenges of early detection in multi-party conversations. Due to ethical and sensitivity concerns, the dataset is not publicly released but will be shared with accredited mental health and suicide-prevention research institutions upon reasonable request.