Interpretable Clustering of Students' Solutions in Introductory Programming

In introductory programming and other problem-solving activities, students can create many variants of a solution. For teachers, content developers, or applications in student modeling, it is useful to find structure in the set of all submitted solutions. We propose a generic, modular algorithm for the construction of interpretable clustering of students' solutions in problem-solving activities. We describe a specific realization of the algorithm for introductory Python programming and report results of the evaluation on a diverse set of problems.