Building the Neural Network-Based System for Identifying the Gaming Addiction Level in Children and Adolescents

This research aims to create a method for detecting mobile gaming addiction levels amongst children and adolescents by developing a mobile application that uses a neural network. The neural network trained on a dataset collected from a sample of 101 young individuals, including mobile device usage data, gaming logs, and the “Chen Internet Addiction Scale” self-reporting questionnaire. The performance of the system was evaluated in terms of accuracy, and its potential for facilitating educational interventions was explored. Preliminary findings suggest this approach to be a valuable tool for adolescents, educators, and parents and provides a non-invasive and non-threatening approach to identifying addiction levels and facilitating early intervention and prevention. The system shows promising results in accurately identifying different levels of gaming addiction and has the potential for educational interventions to prevent gaming addiction in youngsters. This study is an attempt in applying neural networks to identifying a level of mobile gaming addiction. However, future research should validate the proposed system in conjunction with psychology experts and enhance the neural network model by increasing the number of observations and adjusting architectural features.