Scholarlink

Suicide is considered to be a major mental health issue that has affected most individuals worldwide. According to World Health Organization, it shows the rise of suicidal rates among students has increased drastically. This vulnerability shows the rising need to encounter this issue with immediate effect. Therefore, proper detection methods have to be incorporated so that we can reduce the number of suicidal rates. Many computational models were implemented to address this issue. This study was conducted to compare various algorithms such as traditional machine learning models random forest and also various deep learning models like GraphSAGE, Graph Convolutional Network, Convolutional Neural Network, and Convolutional Neural Network with Long Short Term Memory with the proposed GraphSAGE Reinforcement Learning.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Evaluating the Effectiveness of GraphSAGE with Reinforcement Learning in Suicide Risk Prediction

  • 章节

  • 发表日期：

    2026年

查看全文
  • Sherin Rappai,
  • Gobi Ramasamy,
  • V. Rohini,
  • Antonie Bagula

摘要

Suicide is considered to be a major mental health issue that has affected most individuals worldwide. According to World Health Organization, it shows the rise of suicidal rates among students has increased drastically. This vulnerability shows the rising need to encounter this issue with immediate effect. Therefore, proper detection methods have to be incorporated so that we can reduce the number of suicidal rates. Many computational models were implemented to address this issue. This study was conducted to compare various algorithms such as traditional machine learning models random forest and also various deep learning models like GraphSAGE, Graph Convolutional Network, Convolutional Neural Network, and Convolutional Neural Network with Long Short Term Memory with the proposed GraphSAGE Reinforcement Learning.