A Method to Improve Accuracy of Learner Model based on Knowledge and Belief of Learner

The learner model represents essential information about characteristics of learner. The Adaptive Educational Systems and Intelligent Torturing Systems use learner model to adapt required learning services according to characteristics of each learner. Hence, the accuracy of learner model is an important issue. A learner model is called “open” if its parameters could be inspected, discussed or changed by users. In this paper a novel method is proposed to improve accuracy of learner model based on learner knowledge and learner belief about his/her model. For this purpose the overlay learner modeling with Bayesian networks is used to represent learner knowledge. Then according to nature of open learner model, the learner model is presented as skill meter and learner could state his/her belief about it. Then the model is updated through proposed method. Finally the method is evaluated by use of a comprehensive test and t-student test. The results show our method improves accuracy of learner model.