Applying process mining techniques to learning management systems for educational process model discovery and analysis

Abstract

Based on the event logs gathered from the learning management system in use at the Juraj Dobrila University of Pula, this study attempts to discover frequent behavioural patterns in event logs. The process mining tool Fluxicon Disco was used to create, clean and prepare the event log. The discovered process model represents the starting point for the assessment of the usage behaviour of the Moodle LMS. A procedure was developed in R (R-project) to analyse the process model by using various R based packages for business process analysis (bupaR, edeaR, processmapR). By applying process discovery, a subset technique of process mining, a process model is obtained, describing the usage behaviour based on real facts and evidence. This obtained educational process model can be used to tailor the Moodle LMS to the specific needs of the individual courses. Customized workflows for specific courses can be modelled based on the results of the analysis, improving the usability of the learning management system. The significance and importance of this study is achieved by applying process discovery as a rather new approach to improve the Moodle LMS usability with evidence and actual workflows, rather than to assess the learning management system usage by other techniques, e.g. based on users’ perceptions.