Authors: Ms. Neha Yadav, Dr. Nitin Kumar
Abstract: Smartphone addiction has become a growing concern due to excessive dependence on mobile devices for communication, entertainment, and social interaction. This research focuses on a data-centric machine learning framework for detecting smartphone addiction by analyzing user behavioral patterns such as screen time, unlock frequency, app usage, and night-time activity. Unlike traditional model-focused approaches, the proposed framework emphasizes data quality, preprocessing, feature engineering, and reliable labeling to improve prediction performance. The study aims to support early identification of addiction risk and contribute to the development of intelligent digital well-being systems for healthier smartphone usage habits.
