Beyond Risk Prediction: Evidence Grounding and Psychosocial Factor Verification for Explainable Suicide Risk Assessment

查看原文 / View Original 编辑 / Edit

Computer Science > Computation and Language arXiv:2610.08842 (cs) [Submitted on 30 Sep 2026] Title: Beyond Risk Prediction: Evidence Grounding and Psychosocial Factor Verification for Explainable Suicide Risk Assessment Authors: Tianle Hu, Chen Peng, Yi-Hsin Tsai, Takshing Andy Tung, Bingyang Sun, Yenjou Wang.

计算机科学 > 计算与语言 arXiv:2610.08842 (cs) [提交于 2026 年 9 月 30 日] 标题：超越风险预测：用于可解释自杀风险评估的证据溯源与社会心理因素验证作者：Tianle Hu, Chen Peng, Yi-Hsin Tsai, Takshing Andy Tung, Bingyang Sun, Yenjou Wang。

Abstract: Identifying suicide risk from social networking services (SNS) posts is important for detecting suicide-related signals in online environments. However, risk classification alone provides limited insight into the textual evidence and psychosocial factors behind a prediction. Based on the IEEE BigData 2026 Explainable Suicide Risk Detection Challenge, this study presents a framework consisting of Risk Assessment, Evidence Grounding, and Factor Identification.

摘要：从社交网络服务（SNS）帖子中识别自杀风险对于检测在线环境中的自杀相关信号至关重要。然而，仅靠风险分类对于预测背后的文本证据和社会心理因素提供的见解有限。基于 IEEE BigData 2026 可解释自杀风险检测挑战赛，本研究提出了一个包含风险评估、证据溯源和因素识别的框架。

Risk Assessment uses length-based routing to accommodate posts of different lengths. Evidence Grounding identifies supporting phrases and uses a Risk-Evidence constraint to maintain consistency with the Risk prediction. For Factor Identification, two verifiers are used. The Taxonomy Verifier focuses on factor semantics, whereas the Evidence-Aware Verifier uses factor-specific lexical-semantic cues to select informative positive training units. Their prediction probabilities are combined to produce the final factor predictions.

风险评估使用基于长度的路由来适应不同长度的帖子。证据溯源识别支持性短语，并使用风险-证据约束来保持与风险预测的一致性。对于因素识别，使用了两个验证器。分类验证器侧重于因素语义，而证据感知验证器则利用特定因素的词汇-语义线索来选择信息丰富的正向训练单元。它们的预测概率被结合起来以产生最终的因素预测。

The three tasks are evaluated using task-specific F1 score measures. Risk Assessment achieved a Weighted F1 of 0.8088, Evidence Grounding achieved a test Macro row F1 of 0.7605, and Factor Identification achieved a Macro F1 of 0.5562. The results show that the framework can provide risk predictions, along with supporting textual evidence and fine-grained information on psychosocial factors. Overall, the proposed framework extends suicide-risk assessment beyond risk-level prediction and provides a more interpretable analysis of SNS posts.

这三项任务均使用特定任务的 F1 分数指标进行评估。风险评估达到了 0.8088 的加权 F1，证据溯源达到了 0.7605 的测试宏观行 F1，因素识别达到了 0.5562 的宏观 F1。结果表明，该框架能够提供风险预测，以及支持性的文本证据和社会心理因素的细粒度信息。总体而言，所提出的框架将自杀风险评估扩展到了风险等级预测之外，并为 SNS 帖子提供了更具可解释性的分析。