Date
Publisher
arXiv
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.
Study at a glance
- Question: How do student interactions with AI coding assistants align with metacognitive processes, and how do stakeholders perceive them?
- Setting and data: Introductory undergraduate Python course at a Japanese national university, 2023-2025, 248 students, 10,632 dialogue logs, and 11 surveyed computing educators.
- Method: Mixed methods combining thematic analysis of sampled dialogue logs with student pre- and post-questionnaires and educator surveys.
Why it matters
Easy access to AI-generated solutions may lead to metacognitive laziness, where students offload thinking rather than planning, monitoring, and evaluating their work.
Key findings
- Student prompts were heavily dominated by monitoring activities like code correction and verification, with planning and evaluation prompts occurring far less frequently.
- AI responses primarily provided exact solution code during monitoring, which educators and students warned could bypass essential reasoning processes and reduce critical thinking.
- All surveyed educators agreed AI responses should provide indirect scaffolding rather than runnable code, with hints, step-by-step plans, and Socratic questions rated most helpful.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
