Rule-based reasoning for resource recommendation in personalized e-learning

With the increasing of sharing learning resources to enable the resources discovering published on the e-learning systems. The finding suitable learning resource takes too much time because a system retrieves similar resources for all users (or learners) without considering the needs of individual users. This paper proposes a resource recommendation approach for the personalized e-learning based on reasoning rules. The proposed approach designs ontology as a reference ontology which concentrates on describing the learning style appropriate to each learner. The Personalization Rules are defined to support personalized semantic search for heterogeneous learning resources, which deduced by a reasoning engine. Experimental results demonstrate that the proposed approach enables the resource recommendation to individual users, which is originated from multiple sources.