Building context-aware group recommendations in E-learning systems

Abstract

Building group recommendations for students enables to suggest colleagues of similar features, with whom they can learn together by using the same teaching materials. Recommendations should depend on the context of use of an e-learning environment. In the paper, it is considered building context-aware recommendations, which aims at indicating suitable learning resources. It is assumed that learners are modeled by attributes of nominal values. It is proposed to use the method based on the Bayes formula. The performance of the technique is validated on the basis of data of students, who are described by cognitive traits such as dominant learning style dimensions. Experiments are done for real data of different groups of similar students as well as of individual learners. © 2011 Springer-Verlag Berlin Heidelberg.