Identifying Experts from Interaction Behaviour

The interaction behaviours of successful, high-achieving learners when using a Learning Management System (LMS) are different than the behaviours of learners who are having more difficulty mastering the course material. This paper explores the idea that conventional Learning Management Systems can exploit data mining techniques to predict the success or failure of students without requiring the results of formal assessments. This paper describes a study with a second semester computer science class that shows that the success or failure of a learner can be predicted using information about learner interactions with course materials and learner self-reports of subject matter confidence.