Early Prediction of Student Dropout and Performance in MOOCs using Higher Granularity Temporal Information

Abstract

Our project is motivated by the early drop out and low completion rate problem in MOOCs. We have extended traditional features for MOOC analysis with richer granularity information to make more accurate predictions of dropout and performance. The results show that adding final-grained temporal or non-temporal information into behaviour features provides more predictive power in the early phases of a POSA MOOC. As a next step, we plan to determine if we could use these features to better profile students with unsupervised learning methods.