Title: A new approach for the recommendation of relevant learners in CSCL systems

Authors: Zohra Mehenaoui; Yacine Lafifi; Hassina Seridi-Bouchelaghem

Addresses: Department of Computer Science, University Badji Mokhtar Annaba, P.O. Box 12, 23000 Annaba, Algeria; LabSTIC Laboratory, University 8 May 1945 Guelma, P.O. Box 401, 24000 Guelma, Algeria ' LabSTIC Laboratory, University 8 May 1945 Guelma, P.O. Box 401, 24000 Guelma, Algeria ' LabGED Laboratory, University Badji Mokhtar Annaba, P.O. Box 12, 23000 Annaba, Algeria

Abstract: 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.

Keywords: computer-supported collaborative learning; CSCL; learning styles; relevant collaborators; recommendation rule; recommendation criteria; cognitive profile; previous collaborations; collaborator interests; collaboration.

DOI: 10.1504/IJTEL.2016.082311

International Journal of Technology Enhanced Learning, 2016 Vol.8 No.3/4, pp.234 - 252

Received: 23 Feb 2016
Accepted: 05 Aug 2016
Published online: 18 Feb 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article