Use of wearable technologies with machine learning to understand university student learning behaviours to predict students at risk of failing

Abstract

The challenges of effective teaching in mass education environments are well documented. The cohorts of large size generally means that identification of struggling students is usually only at a point when meaningful interventions are too late. This paper reports on the use of novel technologies to provide insights into areas of learner behaviour in large-scale computer programming modules. Accordingly, this paper brings together a previous series of investigative studies of student key engagement points during a typical programming module (1) seat position tracking during programming lectures, (2) Video Lecture Capture viewing behaviours and (3) Student Heart Rate monitoring during lectures. The paper combines the significant findings of each investigation to provide a variety of analysis using Machine Learning (ML) classification modeling. The purpose of the MC study is to create models that could identify students that are likely to pass and those that may be at risk of failing the module.