Learning Peer Support Interactions via Bi-LSTM Graph Neural Networks for Suicide Risk Prediction
Abstract: Suicide prevention through early detection using social media data has been widely studied. However, the critical role of peer support—interactions among individuals with similar mental disorders—has not been deeply investigated or exploited. In this study, we explore peer interactions in online communities for individuals with bipolar disorder and leverage this information to predict suicide risk levels. We propose a model that uses contextualized posts and comments along with their sentiment features. By embedding these features into a peer support network, our model captures peer interactions and predicts suicide risk levels using bidirectional LSTM Graph Neural Networks (Bi-LSTM GNNs). Experimental results demonstrate the effectiveness of our approach, outperforming baseline methods. Our findings highlight the importance of peer comments in predicting suicide risk.
Paper Type: Short
Research Area: Machine Learning for NLP
Research Area Keywords: Graph neural networks, Mental Health, Social Media, Suicide risk prediction
Contribution Types: NLP engineering experiment
Languages Studied: English
Submission Number: 1681
Loading