Development of a Mobile Application Based on a Machine Learning Model to Identify Potential Cases of Smartphone Addiction in School-Aged Adolescents

The pervasiveness of digital devices, especially smartphones, has heightened concerns regarding smartphone addiction among adolescents. This study aims to develop a mobile application that utilizes a high-precision machine learning (ML) model to identify smartphone addiction cases in school-aged adolescents. The ML model, trained using a logistic regression algorithm, uses a dataset of 308 adolescent records. The dataset includes sociodemographic data, smartphone addiction status, and responses based on the short version of the Smartphone Addiction Scale (SAS-SV). The model achieved an accuracy of 92%, indicating its effectiveness in identifying smartphone addiction cases. The Area Under the Curve (AUC) of 0.998 and the F1 score of 0.931 further indicate the model's strong performance. The integration of the ML model into an Android mobile application facilitates accessibility and usability for both parents and adolescents. The application provides real-time results, enabling timely intervention and preventive measures. This study demonstrates the effectiveness of ML in identifying smartphone addiction in adolescents. The mobile application offers a valuable tool for parents, educators, and healthcare professionals to address this growing concern. Future work aims to enhance the model's accuracy and expand the application's functionalities.