A prediction based on clustering and personality questionnaire data for IGD risk: A preliminary work

Abstract

With the development of the Internet, a lot of people trapped in the network, especially the adolescent depending on the network game and disturbing their normal life. 579 freshmen participated in this work who were collected the personality questionnaires in the first week they came in university and their grades points average (GPA) after half year. The questionnaires were including Self-Control (SCS), Barratt impulse Inventory (BIS) and Chinese Big Five Personality (CBF). This work used multi-clustering algorithms to construct the models of predicting for Internet game disorder (IGD) risk, including FCM, K-means, and Hierarchical for training model. This is the first try to predict the risk of IGD by personality traits. The results shown the questionnaire data were well separated by different clustering algorithms into three groups who were shared the analogous personality traits which has a relationship with the behavior of IGD. But compared to the GPA of each group, the efficiency of the prediction model seems not so satisfactory. There need more efforts to optimized the model in the future.