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

TL;DR

This paper presents M-Help, a new social media dataset designed to detect mental health help-seeking signals, diagnose conditions, and identify underlying causes, addressing a critical gap in mental health detection methods.

Contribution

The introduction of M-Help dataset, which uniquely labels help-seeking behavior, specific mental health disorders, and their root causes on social media.

Findings

AI models trained on M-Help effectively identify help-seekers.

Models can diagnose mental health conditions with high accuracy.

The dataset enables uncovering underlying stressors like relationship or financial issues.

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.