Suicide Risk Assessment via Emotion-Time Perception for Social Network Users

Using text data from social network users for suicide risk assessment offers convenience, timeliness, and non-intrusiveness. User emotions are a crucial factor in determining suicide risk and have been extensively studied in research. However, current methods primarily focus on the accumulation of users’ historical emotions, neglecting the changes in emotions and not delving into the time points within historical key emotions. To address this issue, we propose the Emotion-Time-Aware (ETA) model, designed to improve the accuracy of suicide risk assessments. The model consists of three main modules: the Emotional Changes Perception (ECP), the Key Emotion Time Point Perception (KETPP), and the Emotion Perception Fusion (EPF) modules. The ECP module integrates the time, emotion and semantic information of the posts, facilitating the interaction of historical emotions at different time points and capturing the changes in the emotions of users. The KETPP module uses an attention mechanism to identify key emotion time points from users’ historical posts, which are crucial for evaluating suicidal ideation. Finally, the EPF module integrates the emotional changes and key emotion time points to form a comprehensive representation of the users’ posts, thereby assessing their suicide risk level. We evaluate the ETA along with other baseline models on the CLPsych2017 and CLPsych2019 datasets. The results show that the ETA model achieved the highest accuracy and All- F 1 score on both datasets, validating its effectiveness in suicide risk assessment.