Study analyzes student AI interaction patterns in computer science tasks

A new study published on arXiv analyzes student interactions with AI systems, specifically focusing on the types of questions asked during computer science coursework. Researchers developed a few-shot learning approach to classify over 800 student inquiries into 18 categories, using the Graesser et al. taxonomy. The findings indicate that a limited set of question types dominate student interactions, and these question patterns shift significantly as students progress through tasks. AI

IMPACT Provides insights into how students utilize AI for learning, potentially informing the design of more effective AI educational tools.

RANK_REASON The cluster contains a research paper published on arXiv detailing a study on student-AI interaction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• CS2
• DagsHub
• Gotit.pub
• Graesser et al.
• Hugging Face
• Influence Flower
• Litmaps
• ScienceCast
• scite Smart Citations

• paper
• other

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