Scholarlink

This paper is about the use of machine learning methods in the early detection and diagnosis of mental illnesses like anxiety, autism, depression, dementia, and insomnia. We are going to use social media activity and keystroke dynamics to build predictive models of users so that we can identify the signs of mental illness. All from Facebook and twitter and myspace and user behavior and typing rhythm. Logistic Regression, Decision Trees, Random Forest, KNN, SVM, XGB, and a hybrid Stacking Model are all fit and scored using accuracy, precision, recall, F1 score, ROC curve, and AUC. This research shows just how promising machine learning is in making mental illnesses more accessible to diagnose at an earlier age, so that intervention can occur at an early age, and hopefully mental health will be improved. Our findings have significant implications for mental health policy, intervention techniques, and funding allocation in order to achieve the goal of ameliorating the mental health crisis.

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

Predicting Mental Health Ailments Using Social Media Activities and Keystroke Dynamics with Machine Learning

  • 章节

  • 发表日期：

    2025年

查看全文
  • Varad Vishwarupe,
  • Alexander Hankey,
  • Shailesh Pangaonkar,
  • Shwetanshu Shekhar,
  • R. Sheena Rani,
  • Meshari Alwazae,
  • Haazique Sayyed,
  • Vishal Pawar,
  • Vidya Kamma,
  • Priyanka Kuklani

摘要

This paper is about the use of machine learning methods in the early detection and diagnosis of mental illnesses like anxiety, autism, depression, dementia, and insomnia. We are going to use social media activity and keystroke dynamics to build predictive models of users so that we can identify the signs of mental illness. All from Facebook and twitter and myspace and user behavior and typing rhythm. Logistic Regression, Decision Trees, Random Forest, KNN, SVM, XGB, and a hybrid Stacking Model are all fit and scored using accuracy, precision, recall, F1 score, ROC curve, and AUC. This research shows just how promising machine learning is in making mental illnesses more accessible to diagnose at an earlier age, so that intervention can occur at an early age, and hopefully mental health will be improved. Our findings have significant implications for mental health policy, intervention techniques, and funding allocation in order to achieve the goal of ameliorating the mental health crisis.