Automatic generation of deductive logic proof problems

Abstract

When developing intelligent tutoring systems, it is necessary to generate questions that reflect the scope of the material and adapt to a student's individual learning needs. Automatic generation of questions for learning tools can provide variation in the questions generated, while eliminating the time cost for the instructor. For courses teaching deductive logic, web-based tools such as Deep Thought allow students to solve deductive logic proofs set by the instructor and record their progress. Our goal is to automatically generate these proofs in such a way that fulfills the parameters set by the instructors, while using the progress recorded to generate further questions specific to the individual student. © 2011 Springer-Verlag Berlin Heidelberg.