Data Analysis of Short-term and Long-term Online Activities in LMS

Online teaching activities based on increasingly used computer-based educational systems lacks standard rules for its implementation. This paper describes the design of online training activities using Moodle as a Learning Management System (LMS) and, evaluate short-term and long-term students' learning outcomes applying data mining techniques. Clustering and classification algorithms are combined to uncover valuable, non-obvious students' patterns from a well-defined collection of data. Data results from online quiz-based activities in a subject of Computer Science show that students who are not engaged in the training activity during the short-term learning process fail. Data analysis also shows that the number of trials is a key attribute. Hence, it is important to develop user-friendly online activities with real-time feedback based on student behaviour. Moreover, according to our experiment, online training activities decrease in efficiency over time.