Automatic Generation of Analogous Problems to Help Resolving Misconceptions in an Intelligent Tutor System for Written Subtraction

In domains involving procedural skills such as mathematics or programming, students often are prone to misconceptions which result in erroneous solutions. We present the ASG algorithm for generation of analogous problems of written subtraction as an extension of an intelligent tutor system (ITS) proposed by Zinn (2014). The student module of this ITS does not rely on an error library but uses algorithmic de-bugging where an erroneous solution is recognized by identifying which expert rules fail when trying to reproduce the student solution. Since the ITS allows students to create their own subtraction problems, feedback generation must be online and automatic. ASG is a constraint-based algorithm for constructing problems which are structurally isomorphic to the current, erroneously solved student problem