Risk Prediction of Internet Addiction Disorder by Using Social Big Data

Abstract

The purpose of this study is to develop a prediction model about risk factors related to Korean Internet Addiction Disorder, by applying network analysis and decision making-tree analysis to the social big data that are collected from online news sites, blogs, internet cafes, social network service, and internet message boards. The Big Data Document made possible to figure out the decision-making process of Internet Addiction classification through text Mining and factor analysis, which are classified into two categories as ‘general’ and ‘addiction’. A Combination of highest ‘anxiety factor’ and high ‘harmful factor’ had the most influence on Internet addiction. Also, both highest ‘mental health factors’ and high ‘relationship with friends factors’ influenced the most when it comes to Internet addiction. Based on the study, data mining analysis and network analysis of Internet Social Big Data was presented as a prediction model for Internet addiction risk factor, which was considered significant in both policy and analysis methodology.