Predicting Phubbing Through Machine Learning: A Study of Internet Usage and Health Risks

Phubbing, defined as the disruption of social relationships and interactions due to excessive cell phone use, is becoming an increasing concern in modern society. Since one of the primary motivations for cell phone use is internet access, it is crucial to assess the time that individuals spend online to measure the prevalence of phubbing as a social behaviour disorder. This study aimed to better understand and evaluate the phubbing phenomenon by predicting future trends in internet usage using machine learning techniques. Four machine learning models-an artificial neural network (ANN), support vector regression (SVR), random forest (RF) regression, and time series-were employed to predict the average internet usage. Data from 2014 to 2024 were obtained from the World Bank, and cross-validation was used to enhance the reliability and accuracy of the models. All four models were successful in predicting internet usage, with the ANN showing the highest accuracy, followed by SVR, RF, and the time series. According to the data, the average daily time spent online increased from 277 min in 2014 to 417 min in 2024. Projections based on these machine learning models estimate that this figure will rise to 507 min by 2030 and 603 min by 2035. These findings provide valuable insights into the potential risks of increased phubbing behaviours on social interactions and offer a foundation for the exploration of the long-term health implications of excessive internet use. Future research could further examine the effects of phubbing on mental health and develop strategies to mitigate this social behaviour disorder.