A Hybrid Recommender System for E-learning Environments Based on Concept Maps and Collaborative Tagging

Recommender Systems could be used to suggest the items being interested for learners in an e-learning environment. These systems can be useful to recommend learning resources or any other supportive advices to the learners. Different kind of algorithms such as user-based and item-based collaborative filtering have been used to establish a recommender system. With increasing popularity of the collaborative tagging systems, tags could be interesting and useful information which could be considered as part of a metadata to enhance recommender system's algorithms. On the other hand concept maps can be a useful means for learners to visualize their knowledge. Therefore, learners could be supported in their own learning path by recommending concept maps, tags, and learning resources, and also the learning performance of individual learners could be promoted. In this paper, an innovative architecture for a recommender system dedicated to the e-learning environments is introduced. This system simultaneously takes advantage of collaborative tagging and concept maps. By mapping the tags and concepts completed by a learner, incomprehensible facts of his/her knowledge will be identified. Therefore, recommending concept maps containing related and not being understood tags, will be helpful. In the proposed algorithm the similarity of concept maps and tags being labeled by users are computed to achieve the best suggestion.