MindPhone AI: Intelligent Prediction of Smartphone Addiction

Abstract

Smartphones have become an integral part of daily life, especially among students, providing convenient access to communication, education, entertainment, and social networking platforms. However, excessive smartphone usage has been associated with several negative consequences, including smartphone addiction, increased stress levels, poor sleep quality, reduced academic performance, social anxiety, and physical health issues. Recent studies have employed machine learning techniques, natural language processing, wearable sensors, and behavioral analytics to investigate smartphone addiction and stress detection among different populations. Despite these advancements, most existing research focuses on either smartphone addiction or stress prediction independently, with limited efforts toward developing an integrated framework that considers multiple behavioral and psychological factors simultaneously. This study proposes a machine learning-based approach for predicting smartphone addiction and stress levels among students using smartphone usage patterns and behavioral indicators. The proposed system analyzes factors such as screen time, social media usage, sleep duration, academic performance, physical activity, and emotional well-being to identify individuals at risk of excessive smartphone dependency and elevated stress. Various machine learning algorithms, including Random Forest, Support Vector Machine (SVM), XGBoost, and Neural Networks, are utilized to develop predictive models and evaluate their performance. The system aims to classify users into different addiction and stress categories while providing insights into the impact of smartphone usage on students' academic and personal lives. Experimental results are expected to demonstrate the effectiveness of machine learning techniques in early identification of smartphone addiction and stress, enabling timely interventions and promoting healthier digital habits among students. The proposed framework contributes toward the development of intelligent student wellness monitoring systems that support mental health, academic success, and responsible smartphone usage.