Evaluating Adaptive Problem Selection

This paper presents an evaluation study that compares two different problem selection strategies for an Intelligent Tutoring System (ITS). The first strategy uses static problem complexities specified by the teacher to select problems that are appropriate for a student based on his/her current level of ability. The other strategy is more adaptive: individual problem difficulties are calculated for each student based on the student’s specific knowledge, and the appropriate problem is then selected based on these dynamic difficulty measures. The study was performed in the context of the SQL-Tutor system. The results show that adaptive problem selection based on dynamically generated problem difficulties can have a positive effect on student learning performance.