Seybold Report ISSN: 1533-9211
Dr. Rajendra Singh Kushwah, Shah Riteshkumar Rameshchandra, Dr. M V Narayana
Vol 18, No 11 ( 2023 ) | Licensing: CC 4.0 | Pg no: 454-465 | Published on: 30-11-2023
Abstract
The rapid growth of social media platforms has raised concerns about their impact on mental health, leading to the development of techniques for detecting psychological disorders through data mining. This paper proposes a novel system for detecting mental health disorders, particularly in online social network users. Using machine learning techniques, such as Support Vector Machines (SVM), the system is designed to identify at-risk users by analyzing their social media behavior. Key features, including parasocial interactions, online vs. offline communication ratios, and temporal behaviors, are extracted to assess potential mental health issues. The proposed model is evaluated using real datasets from social media platforms like Facebook and Instagram, demonstrating high accuracy in identifying users exhibiting signs of cyber-relationship addiction, net compulsion, and information overload. The results suggest that integrating multiple behavioral and personal features can significantly improve the precision of mental health disorder detection.
Keywords:
Social media mining, Psychological disorder detection, Machine learning, Online social networks, Support Vector Machines (SVM)