An Agent Based Voting System for E-Learning Course Selection Involving Complex Preferences

Abstract

A major potential of agent technologies is the ability to support personalized learning. This is a trend where students are taking more control of their learning in the form of personal choice over topics, activities and tools. In this context, in previous work we presented a multiagent system based on an iterative voting protocol where student agents could vote to decide which courses the university would be running, those courses with little to no interest would be cancelled. This work assumed that the preferences for different courses were independent, which is not always realistic. In this paper, we extend this work and consider complex preferences. In particular, we assume substitutable and complementary preferences between courses. We show that, by using an intelligent voting strategy which tries to predict the voting result, and takes into account the interdependencies between the courses can outperform more naive strategies.