Finding Candidate Helpers in Collaborative E-Learning using Rough Sets

Different computational intelligent techniques are used for classifying data. This paper focuses on the use of rough sets as one of the techniques for classifying the students to determine candidate helpers for collaboration with peers during collaborative e-learning especially in the case of small data set size. This is done through developing MASCE which is a multi-agent system for collaborative E-learning. One of the objectives of this system is to build groups for collaborative learning and to provide best potential helpers for peers. The motivation for building this system is that e-learning has become one of the most popular teaching methods in recent years. At the same time, finding the proper match buddy is an open unsolved problem. The paper shows using the Intelligent Agent approaches which comprise rough sets deduction methodology is a promising solution for this problem even for small data-set size.