Students shift toward How comments for procedural constructs: 94.3% of Multi-Step-Block and 57.3% of Loop-Iteration comments were How comments¶

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? When logic involved multiple steps or repeated actions, students shifted from describing intended outcomes to describing procedures, with How comments at 94.3% for Multi-Step-Block and 57.3% for Loop-Iteration. → rq1-shift

Evidence¶

rq1-shift¶

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 construct-level analysis of classified comments from the four-year Copilot activity (Table 1). The article reports the two construct exceptions to What-comment dominance and states this "suggests that when logic involved multiple steps or repeated actions, students shifted from describing intended outcomes to describing the procedure".

"The exceptions wereMulti-Step-Block, where 94.3% of comments were classified asHow,andLoop-Iteration, where 57.3% were classified asHow."

Discussion¶

Related Claims¶

• Comment revision effort concentrates on Multi-Step-Block and other procedural constructs, with the widest flows ending in Heavy Modification — related
• Low comment rewriting does not imply a smooth process: students describe the main effort as verifying generated code rather than revising prompts — related
• Student specification comments are predominantly natural language, except Return statements which show a high proportion of Strict-Code expressions — related
• Student comments directing AI code generation are dominated by What comments, with How comments second and Why comments rare — related