Enhancing The Error Diagnosis Capability For Constraint-based Tutoring Systems


Nguyen-Thinh Le and Niels Pinkwart

Paper type: 


Constraint-based modelling techniques have been demonstrated a useful means to develop intelligent tutoring systems in several domains. However, when applying CBM to tasks which require students to explore a large solution space, this approach encounters its limitation: it is not well suited to hypothesize the solution variant intended by the student, and thus corrective feedback might be not in accordance with the student's intention. To solve this problem, we propose to adopt a probabilistic approach for solving constraint satisfaction problems.


ITS, weighted constraint-based model, cognitive diagnosis