Thesis Topic: Leveraging MSLQ Data for Predicting Student Achievement Goal Orientations
Collaborative online learning environments such as MOOCs have created new roles and responsibilities for both teacher and learner where the onus of learning is shifting towards learners, and the teacher acts more like a facilitator. These shifted roles have created new motivational, cognitive, and performance challenges for learners. My research investigates the twin discourses of learning analytics, and achievement motivation in the context of online learning systems. My inquiry focuses on: (a) analyzing students’ activity data and building predictive models for identifying behavioral patterns, and (b) motivating a change of behaviour in students for adopting effective learning activities. In my current research project, I am examining how learning motivation and achievement goals relate to a student’s study activities. The ability to predict students’ goal orientations from their online activities will support user-level course adaptations and early interventions to support learning. Previously, we have proposed an empirically validated model of factors influencing educators’ beliefs for adopting an online learning environment. In particular, the model explains how the usage beliefs about the learning analytics of a tool are associated with the intention to adopt the tool.