An agent-based assessing system in data structure course

The research work on e-learning has become very important field in the education. This paper proposes a method to build a Bayesian networks model in order to assess the learnerpsilas knowledge level in data structure course. This e-learning assessing system is designed and implemented based on multi-agent systems. In this paper, an overlay student model based on Bayesian networks is presented. This student modeling is built on organization relationships and dependency relationships among the knowledge items with Bayesian networks. In the data structure course, the dependency relationships among the knowledge items are reflected in this overlay model and the dependency relationships will decide the prediction ability of this model. A case study in data structure course is illustrated in this paper.