Recommendation of Learning Resources and Users Using an Aggregation-Based Approach

The present paper proposes our recommendation approach for the actors of e-learning. It is based on the collaborative filtering approach and some characteristics of e-learning, namely: the roles and interests of actors as well as the representation of learning resources. The main idea is to exploit, in one hand, the roles and the interests to aggregate the actors in communities of roles and/or interests in order to make an initial recommendation (when we do not have the preferences of the actors). On the other hand, the metadata descriptions are used to recommend a new learning resource added (as we have any rating about it) for the appropriate users by computing the similarity between metadata of the new resource and the metadata of the other ones that are considered as favourite resources for the actors.