Mapping of learning style with learning object metadata for addressing cold-start problem in e-learning recommender systems

Abstract

In the e-learning domain, content recommender systems had evolved to recommend relevant learning contents based on the learner preferences. One of the significant drawbacks of content recommenders in the e-learning domain is the new user cold-start problem. The objective of this study is to propose a recommendation model for addressing the cold-start problem using learner's learning style alone. Learning style refers to the way a learner prefers to learn and it is a prominent learner characteristic to understand the learner profile. In this study, we propose an ontology-based recommendation algorithm that makes use of the learning dimensions of the Felder Silverman Learning Style Model to map with the learning object characteristics. The knowledge about the learner and the learning objects are represented using ontology. Experiments were conducted to evaluate the accuracy of the proposed recommendation model using the evaluation metric and f-measure. The learner satisfaction with the proposed model is measured based on the ratings given to the learning objects by the participants of the experiment.