A New Pre-Processing Approach Based on Clustering Users Traces According to their Learning Styles in Moodle LMS

Abstract

Nowadays, many Moroccan universities and institutions start offering training and online courses "E-learning". Which accumulate a vast amount of information that is very valuable for analyzing students’ behavior and could create a gold mine of educational data. However, handling the vast quantities of data generated daily by the learning management systems (LMS) such as Moodle has become more and more complicated. This massive data can be used to improve decision making and management, which requires a proper extracting and cleaning methods.

The purpose of this paper is to suggest a new approach for the preprocessing of the execution traces generated during the interaction of learners with the Moodle LMS and especially the educational content in SCORM format.

In this study, we built two experimental corpus with the learning platform Moodle. Using the data generated by the experimental corpus, we applied the Clustering data mining technique as a preprocessing step in our process discovery. Hence, students with similar learning styles or performance levels are grouped together which should help us to build a partial process model (learning process) that are easier to understand for the decision makers.