Monitoring social anxiety from mobility and communication patterns

Abstract

Mental health problems are a leading cause of disease burden and disability worldwide. The use of mobile and wireless technologies to support the achievement of health objectives (mHealth) has the potential to transform the face of health service delivery. In this paper, we demonstrate how non-invasive mobile sensing technology can be used to passively assess and predict social anxiety among college students. The collected data enhances understanding of how students' social anxiety levels are associated with their mobility and communication patterns. Our analysis based on GPS location, text messages, and call data collected from 54 college students over a two-week period indicates that social anxiety level can be predicted with an accuracy of up to 85%.