Through (Tracking) Their Eyes: Abstraction and Complexity in Program Comprehension

Abstract

Previous studies on writing and understanding programs presented evidence that programmers beyond a novice stage utilize plans or plan-like structures. Other studies on code composition showed that learners have difficulties with writing, reading, and debugging code where interacting plans are merged into a short piece of code. In this article, we focus on the question of how different code-composition strategies and the familiarity with code affect program comprehension on a more abstract, i.e., algorithmic level. Using an eye-tracking setup, we explored how advanced students comprehend programs and their underlying algorithms written in either a merged or abutted (sequenced) composition of code blocks of varying familiarity. The effects of familiarity and code composition were studied both isolated and in combination. Our analysis of the quantitative data adds to our understanding of the behavior reported in previous studies and the effects of plans and their composition on the programs’ difficulty. Using this data along with retrospective interviews, we analyze students’ reading patterns and provide support that subjects were able to form mental models of program execution during task performance. Furthermore, our results suggest that subjects are able to retrieve and create schemata when the program is composed of familiar templates, which may improve their performance; we found indicators for a higher element-interactivity for programs with a merged code composition compared to abutted code composition.