Collaborative optimization algorithm for learning path construction in E-learning

Abstract

In e-learning, learning object sequencing is a challenging task. It is difficult to sequence learning objects manually due to their abundant availability and the numerous combinations possible. An adaptive e-learning system that offers a personalized learning path would enhance the academic performance of learners. The main challenge in providing a personalized learning path is finding the right match between individual characteristics and learning content sequences. This paper presents a collaborative optimization algorithm, combining ant colony optimization and a genetic algorithm to provide learners with a personalized learning path. The proposed algorithm utilizes the stochastic nature of ant colony optimization and exploration characteristics of the genetic algorithm to build an optimal solution. Performance of the proposed algorithm has been assessed by conducting qualitative and quantitative experiments. This study establishes that the hybrid approach provides a better solution than the traditional approach.