Data Mining Approach: Relevance Vector Machine for the Classification of Learning Style Based on Learning Objects

摘要

Recent researches indicate that a lot of effort has been done to provide learners with personalized learning objects. Previous studies classified learning object based on the description of the learning style preference itself without considering student preference. In this study, we propose a data mining approach to the classification of learning objects based on learning style while considering student preference use of the learning objects. Relevance Vector Machine (RVM) is used to build a classifier for the classification of learners. For the purpose of comparison, Support Vector Machine (SVM) and Neural Network (NN) were applied. Comparative simulation results indicated that the propose RVM classifier accuracy and computational time complexity is superior to the NN, and SVM classifiers. The classifier proposes in this research can be of help to educators in proposing appropriate learning objects with high level of accuracy within a short period of time. This in turn can significantly improve learner's performance in understanding the subject matter.