Designing adaptive learning support through machine learning techniques

The use of web 2.0 technologies in web based learning systems has made learning more learner-centered. In a learner centered environment, there is need to provide appropriate support to learners based on individual learner characteristics in order to maximize learning. This requires a Web-based learning system to have an adaptive interface to suit individual learner characteristics in order to accommodate diversity of learner needs and abilities and to maintain an appropriate context for interaction and for achieving personalized learning. The purpose of this paper is to discuss how machine learning techniques can provide adaptive learning support in a Web-based learning system. In this research, two machine learning algorithms namely: Heterogeneous Value Difference Metric (HVDM) and Naive Bayes Classifier (NBC) were used. HVDM was used to determine those learners who were similar to the current learner while NBC was used to estimate the likelihood that the learner would need to use additional materials for the current concept. To demonstrate the concept we used a course in object oriented programming (OOP).