A Voting-Based Agent System for Course Selection in E-Learning

Agent technology is a good approach for solving a number of problems concerned with personalized learning. In personal learning contexts individual students are given an environment that takes into account of their needs, interests and aspirations, and this is intended to lead to an enhanced learning experience. The aim of this paper is to show how agent systems can not only form a good framework for distributed e-learning systems, but also how they can be applied in personal learning contexts where the learners are autonomous and independent. We present an e-learning scenario where students try to register for their preferred courses but where courses will only run if enough students register. In this context, we introduce, for the first time, a prototype of an agent-based voting system in e-learning, where autonomous software agents vote on behalf of the students. We present a number of different voting strategies that student agents could use. Finally, through simulation we empirically investigate the resulting satisfaction of the students in the system.