MACHINE LEARNING TECHNIQUES TO PREDICT SMARTPHONE ADDICTION

Abstract

The rapid proliferation of smartphones has transformed daily life, but excessive usage has led to a growing concern of smartphone addiction, impacting mental health, productivity, and social interactions. Traditional methods for assessing smartphone addiction, such as self-reported questionnaires and surveys, are often subjective, time-consuming, and prone to bias. This research explores the application of machine learning (ML) techniques to predict smartphone addiction using behavioral, usage, and demographic data collected from smartphone users. By leveraging supervised learning algorithms, such as decision trees, random forests, support vector machines (SVM), and neural networks, the system can identify patterns indicative of addictive behavior and classify users according to their risk levels. Experimental results demonstrate that ML-based prediction models achieve high accuracy in detecting potential smartphone addiction, offering a scalable, objective, and proactive approach. The study highlights the potential of integrating ML into mental health monitoring systems, enabling early interventions, personalized recommendations, and improved awareness of smartphone usage patterns.