A trace-based framework for analyzing and synthesizing educational progressions

A key challenge in teaching a procedural skill is finding an ef-fective progression of example problems that the learner can solve in order to internalize the procedure. In many learning domains, generation of such problems is typically done by hand and there are few tools to help automate this process. We reduce this effort by borrowing ideas from test input gen-eration in software engineering. We show how we can use execution traces as a framework for abstracting the character-istics of a given procedure and defining a partial ordering that reflects the relative difficulty of two traces. We also show how we can use this framework to analyze the completeness of expert-designed progressions and fill in holes. Furthermore, we demonstrate how our framework can automatically syn-thesize new problems by generating large sets of problems for elementary and middle school mathematics and synthesizing hundreds of levels for a popular algebra-learning game. We present the results of a user study with this game confirming that our partial ordering can predict user evaluation of proce-dural difficulty better than baseline methods