The Role of Parental Phubbing and Ego-Resilience in Adolescents’ Tendency Toward Digital Game Addiction: A Neural Network Approach

Document Type : Original Article

Author

Assistant Professor, Department of Educational Sciences, Faculty of Literature and Humanities, Hakim Sabzevari University, Sabzevar, Iran

10.22098/jpc.2025.18185.1341

Abstract

Aim: The growing prevalence of digital games and their potential impact on mental health highlight the need to identify protective mechanisms against possible negative effects. The present study aimed to investigate the role of parental phubbing and ego-resilience in adolescents’ tendency toward digital game addiction: a neural network approach.

Method: This research employed a descriptive-correlational design. The statistical population included all male high school students (second cycle) in public schools of Karaj during the 2024 academic year. A total of 300 students were selected using a cluster random sampling method and completed the Digital Game Addiction Scale by Başol et al. (2018), the Parental Phubbing Scale by Ding et al. (2020), and the Ego-Resilience Scale by Block and Kremen (1996). The collected data were analyzed through an artificial neural network using the multilayer perceptron (MLP) approach in SPSS version 26.

Results: The findings indicated that parental phubbing and ego-resilience significantly contributed to predicting digital game addiction among adolescents (p< 0.01). Neural network analysis revealed that parental phubbing positively predicted digital game addiction, whereas ego-resilience negatively predicted it. Parental phubbing emerged as the strongest predictor (100%), while ego-resilience served as a protective factor (57.8%). Moreover, the artificial neural network model accurately captured the trends and variations of digital game addiction based on these variables.

Conclusion: The results demonstrated that parental phubbing and ego-resilience are critical factors in explaining adolescents’ digital game addiction. Moreover, the artificial neural network model showed high accuracy in predicting the intensity and course of this addiction.

Keywords