Automatic Generation of Proof Problems in Deductive Logic

Automatic problem generation for learning tools can provide the required quantity and variation of problems necessary for an intelligent tutoring system. However, this requires an understanding of problem difficulty and corresponding features of student performance. Our goal is to automatically generate new proof problems in Deep Thought – an online propositional logic learning tool – for individual students based on their performance and a set of instructor parameters.. In an initial exploratory study, we evaluate the generated problems compared to the original set of stored problems. This evaluation uses collected student data and instructor feedback.