Toward Inclusive Programming Support for Novice Programmers with Dyslexia: Insights from a Comparative Study

Abstract

Programming attracts a diverse range of learners, including individuals with dyslexia, a learning difficulty that affects reading, writing, and spelling despite average intelligence and educational opportunities. Although prior work has examined dyslexia in natural-language and code comprehension, we still know little about how dyslexic learners engage with code relative to natural language, and what this implies for inclusive programming environments. This gap is especially important in the AI era, as novice programmers increasingly rely on AI-powered coding and learning tools that may not address the distinct comprehension and cognitive support needs of learners with dyslexia. To address this gap, we conducted an eye-tracking study with a mixed-methods design involving 24 novice programmers (12 with dyslexia, 12 without) who completed paired code-comprehension and English-comprehension tasks. We found that although the two groups showed similar overall visual scanning patterns, eye-gaze features suggest higher cognitive effort among dyslexic novices during code comprehension. We also found that the performance gap between dyslexic and neurotypical learners was smaller in code comprehension than in English comprehension, suggesting that programming-specific representations may reshape, rather than eliminate, dyslexia-related challenges. In addition, dyslexic novices reported lower confidence, viewed general training methods as less effective, and described difficulties with symbolic elements and structurally complex code. These findings provide an empirical basis for designing AI-assisted programming tools that can detect cognitive overload and adapt explanations, feedback, and task support to better support dyslexic novices.