From qualitative reasoning models to Bayesian-based learner modeling

Assessing the knowledge of a student is a fundamental part of intelligent learning environments. We present a Bayesian network based approach to dealing with uncertainty when estimating a learner’s state of knowledge in the context of Qualitative Reasoning (QR). A proposal for a global architecture is given. The essentials of the belief network structure for individual scenarios are described, while paying special attention to knowledge aggregation and some design issues that are specific for the domain of QR