Internet addiction and mental health prediction using ensemble learning based on web browsing history

Keyphrases

• Ensemble Learning 100%
• Learning-based 100%
• Internet Addiction 100%
• Mental Health Prediction 100%
• Web Browsing History 100%
• Support Vector Machine 27%
• General Health 27%
• Random Forest 27%
• Gradient Boosting 27%
• General Health Status 27%
• Prediction Accuracy 18%
• Laptop 18%
• GHQ-12 18%
• Internet Addiction Test 18%
• Early Treatment 9%
• Academic Performance 9%
• Universitas Indonesia 9%
• Machine Learning 9%
• Social Life 9%
• RBF Kernel 9%
• Machine Learning Techniques 9%
• Computer Networks 9%
• Undergraduate Students 9%
• Severity Level 9%
• Young People 9%
• Online Shopping 9%
• Health Data 9%
• Information Retrieval 9%
• Instant Messaging 9%
• Web User 9%
• Web Application Firewall 9%
• Leisure Shopping 9%
• Web Browsing 9%
• Social Networking Services 9%
• Web Access 9%
• Mental Health Status 9%
• General Health Questionnaire-12 9%
• University Computer 9%
• Disorder Severity 9%
• Multi-class Prediction 9%

Computer Science

• Ensemble Learning 100%
• Browsing History 100%
• Support Vector Machine 75%
• Random Decision Forest 75%
• Gradient Boosting 75%
• Machine Learning 50%
• Prediction Accuracy 50%
• Test Questionnaire 50%
• Social Media 25%
• Firewall 25%
• Radial Basis Function 25%
• Connected Device 25%
• Extracted Feature 25%
• web user 25%
• Information Retrieval 25%
• Undergraduate Student 25%
• Instant Messaging 25%
• Shopping Online 25%
• Computer Network 25%