An Annotated Dataset for Explainable Interpersonal Risk Factors of Mental Disturbance in Social Media Posts

TL;DR

This paper introduces a new annotated dataset for detecting and explaining interpersonal risk factors like Thwarted Belongingness and Perceived Burdensomeness in social media posts to improve mental health assessment.

Contribution

It provides the first annotated dataset with explanations for IRFs affecting mental disturbance, enabling better NLP models for mental health analysis.

Findings

Baseline models established for IRF detection.

Dataset facilitates future personalized mental health AI research.

Supports real-time social media analysis for mental health risk factors.

Abstract

With a surge in identifying suicidal risk and its severity in social media posts, we argue that a more consequential and explainable research is required for optimal impact on clinical psychology practice and personalized mental healthcare. The success of computational intelligence techniques for inferring mental illness from social media resources, points to natural language processing as a lens for determining Interpersonal Risk Factors (IRF) in human writings. Motivated with limited availability of datasets for social NLP research community, we construct and release a new annotated dataset with human-labelled explanations and classification of IRF affecting mental disturbance on social media: (i) Thwarted Belongingness (TBe), and (ii) Perceived Burdensomeness (PBu). We establish baseline models on our dataset facilitating future research directions to develop real-time personalized AI models by detecting patterns of TBe and PBu in emotional spectrum of user's historical social media profile.