Four-year Copilot comment-specification dataset from an undergraduate OOP course¶
Product or Programme · All products and programmes
Evidence · 5 claims (5 for) · 5 studies (3 associational, 2 qualitative),q2· 0 of 5 report an effect size · 5 claims rest on one study
Description¶
A reconstructed longitudinal dataset of anonymized student comments, Copilot-generated Java code, and test results from four offerings of an undergraduate object-oriented programming activity.
Components¶
Claims¶
- Student specification comments are predominantly natural language, except Return statements which show a high proportion of Strict-Code expressions [+W]
- Low comment rewriting does not imply a smooth process: students describe the main effort as verifying generated code rather than revising prompts [+W]
- Students shift toward How comments for procedural constructs: 94.3% of Multi-Step-Block and 57.3% of Loop-Iteration comments were How comments [+W]
- Student reflections identify speed and scaffolding as the dominant theme, with verification burden, overreliance worries, and prompt precision also prevalent [+W]
- Student comments directing AI code generation are dominated by What comments, with How comments second and Why comments rare [+W]
Related Products and Programmes¶
-
Key Sources¶
- Nasser Giacaman, Valerio Terragni, Paul Denny, and Viraj Kumar. 2026. Commenting with Copilot: A Taxonomy and Multi-Year Analysis of Student Code-Generation Specifications. Proceedings of the 2nd ACM Virtual Global Computing Education Conference (SIGCSE Virtual 2026). https://doi.org/10.1145/3795867.3830978
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
four-year-copilot-comment-specification-dataset-from-an-undergraduate-oop-course |
title |
Four-year Copilot comment-specification dataset from an undergraduate OOP course |
description |
A reconstructed longitudinal dataset of anonymized student comments, Copilot-generated Java code, and test results from four offerings of an undergraduate object-oriented programming activity. |
status |
review |
product_kind |
dataset |
generated |
by process:settle-candidates on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.