Case-based tutoring systems for procedural problem solving on the www

This study proposes a new intelligent tutoring system using case-based student modeling. The proposed system can effectively infer the state of the student's knowledge. The knowledge state is diagnosed through the cases that are generated when the student solves a problem. We have chosen a procedural learning in the physics and designed this domain. In solving this problem, the knowledge types can be divided into the declarative and the procedural knowledge. Procedural knowledge is represented as the graphical case that constitutes a set of nodes and arcs. Declarative knowledge is represented as the analytical case that constitutes attribute-value pairs. In this study, we have implemented the intelligent tutoring system using case-based student model. We have estimated the performance between the human expert and the proposed system to prove the validity of this study. As a result, we have found that the inference method of the proposed system is similar to the human expert.