Daily Smartphone Overdependence Screening Model using Support Vector Machine (Preprint)

Abstract

BACKGROUND Smartphone overdependence has caused many social problems. To overcome these problems, it is necessary to screen and identify smartphone overdependence before it becomes a serious issue. OBJECTIVE We aimed to developed a daily smartphone overdependence screening model using a Support Vector Machine (SVM). METHODS We used smartphone application usage time and frequency data from 224 participants whose ages ranged from their 20s to their 40s. We classified the participants into two groups the smartphone usage control group (SUC) and the smartphone usage disorder addiction group (SUD) using the Korean Smartphone Addiction Proneness Scale (K-SAPS) for Adults. We built a 3-dimensional tensor as the input of machine learning training. This study used the SVM to develop a daily smartphone overdependence screening model. We compared the model performance between the SVM, the Artificial Neural Network(ANN) and the Logistic Regression. RESULTS We identified the frequency of smartphone application usage, age, and marital status as the dominant features of screening smartphone overdependence. Using these features as the inputs of the SVM machine learning model showed a 90% of accuracy for the smartphone overdependence screening. CONCLUSIONS We developed a SVM model, which is a tool for self-control of smartphone daily usage. As a pre-testing tool before visiting a mental health clinic. The SVM model is a powerful analysis method for smartphone overdependence screening. Notably, psychiatry studies have used the SVM when identifying a psychiatric disease. We suggest using the SVM model for smartphone overdependence screening as a smartphone application or intervention system for smartphone dependency management.