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

2026-09-30

AI Summary

This study addresses the lack of textual evidence and psychosocial factor interpretability in suicide risk classification on social networks by proposing an interpretable risk assessment framework. Methodologically, it designs a length-routing mechanism, risk-evidence constraints, and a dual-validator fusion strategy. By integrating NLP-based semantic analysis with probabilistic fusion techniques, the framework jointly models risk assessment, evidence localization, and factor identification. Evaluated on the IEEE BigData Challenge dataset, the model achieves a weighted F1-score of 0.8088 and macro F1-scores of 0.7605 and 0.5562. This work effectively enhances predictive transparency, providing fine-grained, interpretable support for suicide risk intervention.

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. 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. 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.

Problem

• Suicide Risk Assessment
• Explainability
• Evidence Grounding
• Psychosocial Factors
• Social Networking Services

Innovation

• Explainable Suicide Risk Assessment
• Length-based Routing
• Evidence Grounding
• Risk-Evidence Constraint
• Dual Verifiers