Web Usage Mining data preprocessing and multi level analysis on Moodle

This research illustrates the potential of Web Usage Mining on e-Learning domain. We use educational data mining techniques to analyze learners' behavior, to help in learning evaluation and to enhance the structure of a given course. We focus on the preprocessing task, which is considered as the most crucial phase in the whole process. Our objective is to develop a data preprocessing method applied to Moodle logs based on SCORM content structure. In earlier works [1] [2], we proposed a preprocessing tool to implement these new methods and present the first discovered knowledge. In this research, we define new static variables according to the SCORM content tree and we apply more statistics and visualization techniques. In addition, we present multidimensional graphics in order to understand users' accesses. These aggregated variables provide teachers and tutors with interesting knowledge about students' learning process according to different levels of content accessed.