Graesser et al. question taxonomy adapted to student-AI programming interactions¶
Research Method · All research methods
Evidence · 3 claims (3 for) · 1 study (1 associational),q2· 0 of 1 report an effect size · 3 claims rest on one study
Description¶
The article adapts the Graesser et al. taxonomy, which "classifies student questions into 18 categories that reflect different cognitive functions of inquiry, including verification, explanation, causal reasoning, procedural guidance, and evaluation". Originally developed for tutoring dialogue, it is repurposed to distinguish prompts seeking conceptual clarification, procedural guidance, debugging explanations, and confirmation of correctness in programming contexts. The article applies it via a few-shot LLM classification approach to 830 CS2 student-AI prompts.
Accounts¶
- The Graesser et al. question taxonomy adapted to student-AI programming interactions: The article adapts the Graesser et al. taxonomy, which "classifies student questions into 18 categories that reflect different cognitive functions of inquiry, including verification, explanation, causal reasoning, procedural guidance, and evaluation". Originally developed for tutoring dialogue, it is repurposed to distinguish prompts seeking conceptual clarification, procedural guidance, debugging explanations, and confirmation of correctness in programming contexts. The article applies it via a few-shot LLM classification approach to 830 CS2 student-AI prompts. (Matin Amoozadeh et al. (2026))
Claims¶
- A small subset of question types accounts for the majority of student inquiries to AI, with Assertion the most frequent category in both CS2 sessions [+M]
- Students' question types shift from confusion-reporting toward procedural and task-oriented inquiry as tasks progress, though the session difference did not reach conventional significance [+M]
- Continuing-generation students showed higher usage of procedural and directive question types, while first-generation students leaned toward verification and expectational questions [+M]
Related Research Methods¶
Key Sources¶
- Matin Amoozadeh and Amin Alipour. (2026). Analysis of Types of Inquiries in Student-AI Interaction: A case study of two CS2 tasks. https://arxiv.org/abs/2608.17919
Page metadata
| Field | Value |
|---|---|
type |
research-method |
id |
graesser-et-al-question-taxonomy-adapted-to-student-ai-programming-interactions |
title |
Graesser et al. question taxonomy adapted to student-AI programming interactions |
description |
The article adapts the Graesser et al. |
status |
review |
generated |
by process:settle-candidates on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.