Smart Phone Addiction Classification

The increasing dependence on smartphones has led to rising concerns about smartphone addiction, particularly among students and working professionals. Excessive usage affects mental health, sleep quality, and productivity, making early detection of addiction essential. This project presents a smartphone addiction classification system using machine learning techniques to identify and categorize user behavior based on usage patterns. Data such as screen time, app usage frequency, notification response time, and call or message duration are collected and analyzed to determine addiction levels. machine learning algorithms, including Random Forest are trained to classify users into normal, moderate, and high addiction categories. The model provides accurate insights into user habits and helps in understanding the correlation between device usage and addiction tendencies. By offering a data-driven approach to behavioral monitoring, the system aims to promote digital well-being and support users in achieving a healthier balance between technology use and daily life.