A hybrid SEM-neural network analysis of social media addiction

Abstract Social media has been a phenomenon but it is a double-edge sword that can bring about negative effects such as social media addiction. Nevertheless, very less attention has been given in unveiling the determinants of social media addiction. In this study, artificial intelligence and expert systems were applied through a hybrid SEM-artificial neural network approach to predict social media addiction. An integrated model of the Big Five Model and Uses and Gratification Theory was validated based on a sample of 615 Facebook users. Unlike existing social media studies that used SEM, in this study, we engaged a hybrid SEM-ANN approach with IPMA as the additional analysis. The new SEM-IPMA-ANN analysis is a novel methodological contribution where useful conclusion can be drawn based on not only the construct's importance but also its performance in prioritizing managerial actions. Primary focus will be given in improving the performance of constructs that exhibit huge importance with relatively low performance. Based on the normalized importance of the ANN analysis using multilayer perceptrons with feed-forward-back propagation algorithm, we found nonlinear relationships between neuroticism and social media addiction. This is a significant finding as previously only linear relationships were found. In addition, entertainment is the strongest predictor followed by agreeableness, neuroticism, hours spent and gender. The artificial neural network is able to predict social media addiction with an 86.67% accuracy. The new methodology and findings from the study will give huge impacts to the extant literature of expert systems and artificial intelligence generally and social media addiction specifically. We discussed the methodological, theoretical and practical contributions of the study.