Early Prediction of Student Dropout in MOOCs
摘要
This study addresses the prevalent challenge of high dropout rates in Massive Open Online Courses (MOOCs) by leveraging learning analytics for the early identification of at-risk students. Drawing upon Fredricks’s engagement model, which posits student engagement as a critical determinant of learning success, this research analyzes comprehensive data from the “Statistical Learning4” course offered on Stanford’s Lagunita platform during Winter 2015 and Winter 2016. The rich dataset, capturing detailed student interactions within the MOOC environment, enables an in-depth investigation of behavioral patterns associated with disengagement and dropout. By employing advanced analytical techniques, this study aims to develop predictive models capable of identifying at-risk students early in their enrollment, facilitating timely interventions designed to improve retention and ultimately contribute to greater success in MOOC-based learning.