Unobtrusive Stress Assessment Using Smartphones

Stress assessment is a complex issue and numerous studies have examined factors that influence stress in working environments. Research shown monitoring individuals' behaviour parameters during daily life can also help assess levels. In this study, we examine of work-related using features derived from sensors smartphones. particular, use information physical activity levels, location, social-interactions, social-activity, application usage days. Our study included 30 employees chosen two different private companies, monitored over period 8 weeks real work The findings suggest phone shows important correlation with perceived level. Second, used machine learning methods to classify levels based on the analysis provided by We decision trees obtaining 67.57 percent accuracy 71.73 after applying semi-supervised method. results show be unobtrusive manner, through smartphone data.