Patterns in Elementary-Age Student Responses to Personalized & Generic Code Comprehension Questions

The CS community has struggled to assess student learning at the K-8 level, with techniques ranging from one-on-one interviews to written assessments. While scalable, automated techniques exist for analyzing student code, a scalable method for assessing student comprehension of their own code has remained elusive. This study is a first step in bridging the gap between the knowledge gained from interviews and the time efficiency and scalability of written assessments and automated analysis. The goal of this study is to understand how student answers on various types of questions differ depending on whether they are being asked about their own code or generic code. We find that while there were no statistically-significant differences in overall scores, questions about generic and personalized code of comparable complexity are far from equivalent. Our qualitative analyses revealed interesting patterns in student responses, inviting further research into this assessment technique. In particular, students answered differently from students with generic code when presented with individual blocks from their code taken out of context and placed into different code snippets, and students answered in a way that demonstrates a functional, instead of structural, understanding on Explain in Plain English (EiPE) questions.