Adapting Deep Learning Methods for Mental Health Prediction on Social Media

Ivan Sekulic and Michael Strube
Heidelberg Institute for Theoretical Studies


Abstract

Mental health poses a significant challenge for individual’s well-being. Text analysis of rich resources, like social media, can contribute to deeper understanding of illnesses and provide means for their early detection. We tackle a challenge of detecting social media users’ mental status through deep learningbased models, moving away from traditional approaches to the task. In a binary classification task on predicting if a user suffers from one of the nine different disorders, hierarchical attention network outperforms previously set benchmarks for four of the disorders. Furthermore, we explore the limitations of our model and analyze phrases relevant for classification by inspecting model’s word-level attention weights.