A New Approach for the Recommendation of Relevant Learners in CSCL Systems

Résumé fourni par la source

In collaborative learning environments, finding the right collaborator is critical for collaboration and sharing experience. In this work, we propose a new method to recommend relevant collaborators in a collaborative learning environment. The proposed approach is based on the similarity calculation between target learner and candidate learner by using some 'relevance criteria'. These criteria consider the cognitive profile of learner, his learning style according to Felder-Silverman model, his interests and his previous collaborations. A set of recommendation rules were established to measure the proposed recommendation criteria. To validate the proposed rules and formulas, a computer-supported collaborative learning system has been implemented and tested. In fact, the developed system was tested in a higher education establishment where obtained results were very encouraging.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.