M-HELP: Using Social Media Data to Detect Mental Health Help-Seeking Signals

2025-08-21

AI Summary

Existing mental health datasets lack fine-grained annotations of active help-seeking behavior, hindering data-driven modeling of early psychological crisis detection. Method: We introduce M-Help, the first social media dataset explicitly designed for active help-seeking identification, systematically annotated with three complementary labels: (1) help-seeking behavior (binary), (2) mental health condition type (e.g., depression, anxiety), and (3) underlying causal factors (e.g., interpersonal conflict, financial stress). We propose a multi-task deep learning framework that jointly models help-seeking intent recognition, mental health condition classification, and causal factor extraction. Results: Our model significantly outperforms single-task baselines across all subtasks: achieving an F1-score of 0.89 for help-seeking detection, a 6.2% improvement in condition classification accuracy, and an 8.5% gain in Macro-F1 for causal factor identification. M-Help and the proposed framework provide an interpretable, deployable foundation for scalable early psychological intervention.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Machine Learning: Active Learning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Large pretrained models with web data
• Social Networks and Social Media: Social mining and social search on the Web

Abstract

Mental health disorders are a global crisis. While various datasets exist for detecting such disorders, there remains a critical gap in identifying individuals actively seeking help. This paper introduces a novel dataset, M-Help, specifically designed to detect help-seeking behavior on social media. The dataset goes beyond traditional labels by identifying not only help-seeking activity but also specific mental health disorders and their underlying causes, such as relationship challenges or financial stressors. AI models trained on M-Help can address three key tasks: identifying help-seekers, diagnosing mental health conditions, and uncovering the root causes of issues.

Problem

• Detecting mental health help-seeking signals on social media
• Identifying specific mental health disorders from online content
• Uncovering root causes like relationship or financial stressors

Innovation

• Novel dataset for help-seeking behavior detection
• AI models identify help-seekers and diagnose conditions
• Uncovering root causes of mental health issues