Tools for predicting drop-off in large online classes

Abstract

This paper describes two diagnostic tools to predict students are at risk of dropping out from an online class. While thousands of students have been attracted to large online classes, keeping them motivated has been challenging. Experiments on a large, online HCI class suggest that the tools these paper introduces can help identify students who will not complete assignments, with an F1 score of 0.46 and 0.73 three days before the assignment due date.