Constraint-Based Modelling (CBM) is a student modelling techniquethat is rapidly maturing. We have implemented several tutors using CBM anddemonstrated its suitability to open-ended domains in particular. A problemwith open-ended and complex domain models is their large size, necessitating acomprehensive problem set in order to provide sufficient exercises for extendedlearning sessions. We have addressed this issue by developing an algorithm thatautomatically generates new problems directly from the domain knowledgebase. We present the algorithm and compare students’ performance withgenerated problems to those using a teacher-authored problem set, and show theperformance of the generated problem set to be superior.
展开▼