Scaffolding Metacognition in Programming Education: Understanding Student-AI Interactions and Design Implications
This addresses the problem of AI potentially undermining learning in programming education for students and educators, offering incremental insights for tool design.
The study investigated how generative AI tools like ChatGPT affect novice programmers' metacognitive processes by analyzing over 10,000 dialogue logs and surveys, finding that current interactions often bypass key learning strategies and providing design guidelines to better support metacognition.
Generative AI tools such as ChatGPT now provide novice programmers with unprecedented access to instant, personalized support. While this holds clear promise, their influence on students' metacognitive processes remains underexplored. Existing work has largely focused on correctness and usability, with limited attention to whether and how students' use of AI assistants supports or bypasses key metacognitive processes. This study addresses that gap by analyzing student-AI interactions through a metacognitive lens in university-level programming courses. We examined more than 10,000 dialogue logs collected over three years, complemented by surveys of students and educators. Our analysis focused on how prompts and responses aligned with metacognitive phases and strategies. Synthesizing these findings across data sources, we distill design considerations for AI-powered coding assistants that aim to support rather than supplant metacognitive engagement. Our findings provide guidance for developing educational AI tools that strengthen students' learning processes in programming education.