Lightme: Analysing Language in Internet Support Groups for Mental Health

TL;DR

This paper develops a machine learning-based classifier to identify crisis posts in online mental health support forums, highlighting linguistic features associated with severe posts and demonstrating competitive performance using only text features.

Contribution

It introduces a novel approach for classifying crisis posts in mental health forums using NLP and ML, with insights into key linguistic indicators of crisis situations.

Findings

Lexical resource features improved crisis post classification accuracy to 52%.

Six linguistic characteristics are strongly associated with crisis posts.

A text-only feature set can effectively support triage in mental health online forums.

Abstract

Background: Assisting moderators to triage harmful posts in Internet Support Groups is relevant to ensure its safe use. Automated text classification methods analysing the language expressed in posts of online forums is a promising solution. Methods: Natural Language Processing and Machine Learning technologies were used to build a triage post classifier using a dataset from Reachout mental health forum for young people. Results: When comparing with the state-of-the-art, a solution mainly based on features from lexical resources, received the best classification performance for the crisis posts (52%), which is the most severe class. Six salient linguistic characteristics were found when analysing the crisis post; 1) posts expressing hopelessness, 2) short posts expressing concise negative emotional responses, 3) long posts expressing variations of emotions, 4) posts expressing dissatisfaction with available health services, 5) posts utilising storytelling, and 6) posts expressing users seeking advice from peers during a crisis. Conclusion: It is possible to build a competitive triage classifier using features derived only from the textual content of the post. Further research needs to be done in order to translate our quantitative and qualitative findings into features, as it may improve overall performance.