Identifying Factors and the Relationship between Problematic Social Media Use and Anxieties in Instagram Users: A Deep Investigation-based Dual-stage SEM-ANN Analysis

Abstract

This paper aims to identify the factors and the relationship between Problematic Social Media Use (Compulsion and Withdrawal) and Anxieties in Instagram users. The research is descriptive, with a quantitative approach developed through a survey (n=757). After a multi-analytical approach using Covariance-based Structural Equation Modeling (CB-SEM) validated the model, results became inputs to an Artificial Neural Network (ANN) model to predict the Anxieties. Findings pointed out that the most relevant constructs were Shared Content Anxiety and Self Evaluation Anxiety, and the neural network provided empirical evidence to support that Compulsion is the most relevant predictor for Anxieties, increasing its effects. The introduction of this new methodology and the theoretical contribution of the proposed hybrid model opens perspectives of the existing body of knowledge in the literature related to understanding phenomena such as the relationship between Problematic Social Media Use and Anxieties in Instagram users.