Evaluating Student Learning Effect Based on Process Mining

As education is taking an increasingly significant role in society today, efficient and precise evaluation of student learning effect is calling for more attention. With recent advances of information technology, learning effect can now be evaluated via mining student’s learning process. This paper proposes an interactive student learning effect evaluation framework which focuses on in-process learning effect evaluation. In particular, our proposal analyzes students modeling assignment based on their operation records by using techniques of frequent sequential pattern mining, user behavior analysis, and feature engineering. In order to enable effective student learning evaluation and deliver practical value, we have developed a comprehensive online modeling platform to collect operation data of modelers and to support the corresponding analysis. We have carried out a case study, in which we applied our approach to a real dataset, consisting of student online modeling behavior data collected from 24 students majoring in computer science. The results of our analysis show that our approach can effectively and practically mine student modeling patterns and interpret their behaviors, contributing to assessment of their learning effect.