Emotion-Aware LSTM Networks for Detecting Suicide Notes

Abstract

Suicide represents a critical global public
health issue, causing over 700,000 lives each year,
particularly among young people. Emotional distress,
dysregulation, hopelessness, and psychache are key
risk indicators. In the digital era, individuals increasingly
express suicidal thoughts through text on social media,
offering valuable insights into mental states.
In this study, we propose a computational approach to
classify suicide notes based on sentence-level emotional
content.