Study analyzes student use of AI coding assistants for code generation

A new study published on arXiv analyzes how students use AI coding assistants like Copilot to generate code based on natural language specifications. Researchers developed a taxonomy to categorize comments based on type, expression level, and code construct, finding that students primarily used natural language for 'what' comments and focused more on verifying generated code than on rewriting specifications. The analysis covered a four-year dataset of undergraduate programming submissions and reflections. AI

IMPACT Provides insights into how students interact with AI coding tools, potentially informing educational strategies and AI development.

RANK_REASON The cluster contains a research paper published on arXiv detailing an analysis of student code generation specifications. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• Copilot
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• Litmaps
• ScienceCast
• scite Smart Citations

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →