Data Mining in Personalizing Distance Education Courses

The need to personalize distance education courses stems from their ultimate goal: the need to serve an individual student independently of time, place, or any other restrictions. This means that a distance education system should be served by a data mining system (DMS) to monitor, intervene in, and counsel the teachingstudying-learning process. Compared to intelligent tutoring systems or adaptive learning environments where a teacher has only an occasional role, a DMS emphasizes the role of expert, in this case teacher, to interpret the findings obtained from analysing the data retrieved from the course. A DMS was designed and implemented to analyse the study records of two programming courses in a distance curriculum of Computer Science. Various data mining schemes, including the linear regression and probabilistic models, were applied to describe and predict student performance. The results indicate that a DMS can help a distance education teacher, even in courses with relatively few students, to intervene in a learning process at several levels: improving exercises, scheduling the course, and identifying potential dropouts at an early phase.