Learning Style Deriving Approach to Personalize E-Learning Material Resources

Personalized recommender systems in e-learning environment make the learning process more effective and efficient. In this paper, we present a detailed knowledge-based system design for personalizing the e-learning material resources. Initially, the approach rates the different learning styles according to the learner personal data and preferences, and then it personalizes the learning material resource type, the material abstraction level, and the learning session time. The learning material resources are recommended to the learner in two alternatives: the learning material resources of the most-ranked learning style to learner or an ordered list of material learning resources based on the learning styles ranking. To show how the approach is very beneficial in e-learning systems, we present a case study with different usage scenarios.