Descriptive and Predictive Modeling of Student Achievement, Satisfaction, and Mental Health for Data-Driven Smart Connected Campus Life Service

Abstract

Yonsei University in Korea launched an educational innovation project entitled "Data-Driven Smart-Connected Campus Life Service", for which student-related data have been accumulated at university level since spring of 2015, and descriptive, predictive and prescriptive modeling have been conducted to offer innovative education service to students. The dataset covers not only conventional student information, student questionnaire survey, and university administrative data, but also unconventional data sets such as student location data and learning management system (LMS) log data. Based on the datasets, with respect to 4,000+ freshman students at residential college, we conducted preliminary implementation of descriptive and predictive modeling for student achievement, satisfaction, and mental health. The results were overall promising. First, descriptive and predictive modeling of GPA for student achievement presented a list of significant predictive variables from student locations and LMS activities. Second, descriptive modeling of student satisfaction revealed influential variables such as "improvement of creativity" and "ability of cooperation". Third, similar descriptive modeling was applied to students' mental health changes by semesters, and the study uncovered influential factors such as "difficulty with relationship" and "time spent with friends increased' as key determinants of student mental health. Although the educational innovation project is still in its early stages, we have three strategies of the future modelling efforts: They are: (1) step-by-step improvement from descriptive, predictive, to prescriptive modelling; (2) full use of recurring data acquisition; (3) different level of segmentation.