%0 Journal Article
%T Learner Clustering and Association Rule Mining for Content Recommendation in Self-Regulated Learning
%A Ahmad A. Kardan
%A Nahid Ghassabzadeh Saryazdi
%A Hamed Mirashk
%J International Journal of Computer Science Research and Application
%D 2012
%I INREWI Publications
%X Grouping e-learners based on their model in the e-learning environment is a key issue to build a personalized learning system. Recommender Systems can be useful to recommend learning resources or any other supportive advices to the learners. These systems could be used to suggest the contents being interested for learners in an e-learning environment. Different kind of algorithms such as user-based and item-based collaborative filtering have been used to establish a recommender system. In this paper, an innovative architecture for a recommender system (AELTRec) dedicated to the e-learning environments is introduced. This architecture simultaneously takes advantages of K-Means clustering technique and association rule mining. We first build a learner model based on PAPI learner model, which is the basis of learner grouping. Furthermore, K-Means is used to cluster the e-learner types. When groups of related interests have been established, the association rule mining techniques will be used to elicit the rules of the best content for each learner. Based on e-Learner groups, users can obtain content recommendation from the group¡¯s opinions. Also this architecture considers the learner self-monitoring ability in his/her, constantly evaluates learning activities, the results of the activities, and provides warning messages from the system to the learner. It was expected that the proposed architecture has excellent performance.
%K Personalization
%K Recommender Systems
%K Clustering Techniques
%K Association Rule Mining
%K E-learning
%U http://www.ijcsra.org/v2i1-Kardan1.pdf