A Learner Model Reason Maintenance System

Learner Modeling is a dynamic process. Creating and maintaining models of learners by an interactive system is not a precise task, and it requires guesses and abductive generation of explanation of the learners’ actions. In addition, learners change their behavior while interacting with the system. Therefore, these systems need some mechanisms to maintain the rationality of the learner models created. For this maintenance to be rational, we enunciate two basic principles: system consistency and learner accuracy. We present a system AMMS (Agent Model Maintenance System) to maintain learner models in accordance with these two principles, which were followed by introducing reasons (endorsements) for the hypotheses created about the learner. These reasons (which are based on the acquisition rules) are kept in the AMMS, so it is possible to choose the most trustable learner model by using a "trust" function.