The utilization of data analysis techniques in predicting student performance in massive open online courses (MOOCs)

Abstract

The growth of the Internet has enabled the popularity of open online learning platforms to increase over the years. This has led to the inception of Massive Open Online Courses (MOOCs) that globally enrol millions of people. Such courses operate under the concept of open learning, where content does not have to be delivered via standard mechanisms that institutions employ, such as physically attending lectures. Instead learning occurs online via recorded lecture material and online tasks. This shift has allowed more people to gain access to education, regardless of their learning background. However, despite these advancements, completion rates for MOOCs are low. The paper presents our approach to learner predication in MOOCs by exploring the impact that technology has on open learning and identifies how data about student performance can be captured to predict trend so that at risk students can be identified before they drop-out. The study we have undertaken uses the eRegister system, which has been developed to capture and analyze data. The results indicate that high/active engagement, interaction and attendance is reflective of higher marks. Additonally, our approach is able to normalize the data into consistent a series so that the end result can be transformed into a dashboard of statistics that can be used by organizers of the MOOC. Based on this, we conclude that there is a fundamental need for predictive systems within learning communities.