System for identifying the level of mobile gaming addiction in children and adolescents

Abstract

This research paper describes a system for identifying the level of mobile gaming addiction in children and adolescents using data collected from mobile electronic devices. The system includes a mobile application that collects usage data on mobile games and uses a neural network model based on an "autoencoder" architecture to detect addiction levels. The neural network model includes the error back propagation algorithm and was trained on parameters selected from Chen Scale (CIAS) for addiction level detection. A prototype of the mobile application was created and adequate estimates of the neural network model quality were obtained. Future work will involve validation of the system with psychologists and further improvement of the neural network model by increasing the number of observations and adjusting the architecture. The results of this study demonstrate the potential of using neural networks and mobile technology to identify and monitor mobile gaming addiction in children and adolescents, which can aid in early intervention and prevention efforts.

Keywords

• gaming addiction
• neural network
• internet gaming disorder
• video game addiction
• mobile gaming disorder