Enhancing educational data mining techniques on online educational resources with a semi-supervised learning approach

Abstract

Both educational data mining (EDM) and learning analytics (LA) focus on applying analytics and data mining techniques to extract useful information from large data sets. EDM is generally more interested in automated methods for discovery within the educational data while LA is relatively keen on applying human-led methods to understand the involved learning processes. Among the various fields of challenging studies in EDM, domain structure discovery is aimed to find the structure of knowledge in an educational domain, such as formulating the prerequisite requirements among various knowledge components through online educational resources. However, with the vast amount of knowledge components in specific subjects, the process of such formulation is very complicated and time-consuming no matter being done manually or semi-automatically. In this work, we propose a systematic framework of a semi-supervised learning approach in which a concept-based classifier is co-trained with an explicit semantic analysis (ESA) classifier to derive a common set of prerequisite rules based on a diverse set of online educational resources. To demonstrate its feasibility, a working prototype is built with some impressive results obtained in specific engineering subjects. More importantly, our proposal sheds light on many possible directions for future exploration. © 2015 IEEE.