A dynamic self-organizing e-learner communities with improved multi-agent matchmaking algorithm

Abstract

Learning experiences and resources sharing is becoming one of the most important research fields of the advanced E-Learning techniques. This paper proposed a dynamic self-organizing community mechanism with an improved matchmaking algorithm, which makes the systems having the ability of self-organizing community that groups similar agents according to their preferences and capabilities. How to represent, evaluation, exchange as well as how to matchmaking during the self-organizing process are discussed in the algorithms. A prototype is also built to verify the algorithms. Experiments based on rea learner data have shown that this mechanism can organize learners properly, and has sustainably improved speed and efficiency of searches for peer students owning relevant knowledge resources.