Automatic Problem Generation in Constraint-Based Tutors

Constraint-Based Modelling (CBM) is a student modelling technique that is rapidly maturing. We have implemented several tutors using CBM and demonstrated its suitability to open-ended domains in particular. A problem with open-ended and complex domain models is their large size, necessitating a comprehensive problem set in order to provide sufficient exercises for extended learning sessions. We have addressed this issue by developing an algorithm that automatically generates new problems directly from the domain knowledge base. We present the algorithm and compare students’ performance with generated problems to those using a teacher-authored problem set, and show the performance of the generated problem set to be superior