Suicide thoughts screening with social media using cat swarm-intelligent adaptive recurrent network

Abstract

The research on detecting suicidal ideation through social media in early stages and faces several difficulties. Many persons with a propensity for suicide express their ideas and beliefs on social media. Numerous studies have found that accessible social media posts have useful criteria for rapidly identifying people thosewho are considering suicide. Finding and comprehending the risk factors and warning signals that may lead to suicide, is the most challenging aspect of suicide prevention. By automatically detecting the abrupt changes in a user behavior, this can be accomplished. Social media interactions can be used to gather textual and behavioral data using natural language processing (NLP) techniques. The framework can use this data to spot trends in social interactions that point to suicide intent. We can anticipate suicidal ideation using classification techniques based on deep learning. We can accomplish this by identifying these emotions in user postings using a combination of Cat Swarm-Intelligent Adaptive Recurrent Network (CSI-ARN) models. Adding extra training data and using an attention model to improve model performance can increase accuracy. This study examines social media comments for suicidal thoughts using a CSI-ARN model. The suggested model outperformed baseline models with 90.3% accuracy and 92.6% F1-score.