Investigating Students' Learning in Online Learning Environment

Due to the increasing interest in the online learning environment, particularly in Massive Open Online Courses (MOOCs), predictions and education data mining have rapidly gained prominence in education studies over the past decade. The massive amount of student data available in MOOC platforms enables us to gain insight into students’ learning behaviours. Therefore, this paper outlines the doctoral work that explores the idea of ‘student roles’ and their linguistic changes to analyse the students’ learning behaviours in MOOCs. A multi-class classifier has been built to identify user roles (e.g. information seeker, information giver) with 82.30% F-measure. Preliminary results on linguistic experiments demonstrate, distinguish linguistic behaviours can be observed in different user roles. The outcome of this research study will contribute to a learning model that can be used to understand students’ learning process.