Abstract
E-learning settings such as on-line courses offered in China often involve large numbers of geographically dispersed students who have diverse professional background, learning preferences, and disparate learning needs. However, current e-learning and classroom teaching methods are extremely limited with respect to personalized learning as they typically provide the same content to all students. Hence, students are finding it difficult to make a decision about which learning materials best meet their personal demands, whilst instructors are finding it almost impossible to recommend personalized materials most appropriate to students since the individual study situations are disparate and hard to analyze. This paper proposes an e-learner Community Building strategy based on Hebbian Learning Rule, which helps learners to set up trusted neighbor connections to peer students with similar study situations. In addition, students can get useful recommendations for proper learning resources from their peers. Based on this theory a recommendation platform has been developed that enables a learner to enquire recommendations, vote on recommended resources and communicate with neighbor learners. Experimental results derived from real learner data have shown that this system can organize learners properly and efficiently, and the cooperative recommendation service indeed improves the students' learning achievements.