Dropout Prediction in MOOCs using Learner Activity Features

This special issue of the eLearning Papers is based on the contributions made to the EMOOCS 2014 conference jointly organized by the École Polytechnique Fédérale de Lausanne (EPFL) and P.A.U. Education. Download Print Version.
Dropout Prediction in MOOCs using Learner Activity Features
By Sherif Halawa, Daniel Greene, John Mitchell. While MOOCs offer educational data on a new scale, many educators have been alarmed by their high dropout rates. Learners join a course with the motivation to persist for some or the entire course, but various factors, such as attrition or lack of satisfaction, can lead them to disengage or totally drop out. Educational interventions targeting such risk factors can help reduce dropout rates. However, intervention design requires the ability to predict dropouts accurately and early enough to allow for timely intervention delivery. In this paper, we present a dropout predictor that uses student activity features to predict which students have a high risk of dropout. The predictor succeeds in red-flagging 40% - 50% of dropouts while they are still active. An additional 40% - 45% are red-flagged within 14 days of absence from the course. More...