Student comments directing AI code generation are dominated by What comments, with How comments second and Why comments rare¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Across four cohorts, 77.0% of analyzed comments were What comments, 21.0% How comments, and only 0.4% Why comments. → rq1-dist

Evidence¶

rq1-dist¶

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

q2 · i? · associational · r2

Aggregate analysis of LLM-classified comments from a four-year Copilot activity (1,161 students, 52,172 analyzed comment instances). The article reports "comments were dominated byWhatcomments (77.0%)" with How at 21.0% and Why at 0.4%; no effect size is printed.

"Overall, comments were dominated byWhatcomments (77.0%), followed byHowcomments (21.0%), whileWhycomments were rare (0.4%)."

Discussion¶

Related Claims¶

• Students rarely rewrite specification comments: within the first 10 attempts, Unchanged (48.4%) and New (41.3%) dominate while substantial revisions total only 4.4% — related
• Students shift toward How comments for procedural constructs: 94.3% of Multi-Step-Block and 57.3% of Loop-Iteration comments were How comments — related
• Comment revision effort concentrates on Multi-Step-Block and other procedural constructs, with the widest flows ending in Heavy Modification — related