Unedited voice prompts have lower odds of first-attempt success than text prompts on two of three Prompt Problems¶

Claim · All claims
Evidence · 1 study · associational r2 · q3
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Students who initially used unedited voice prompting had lower odds of immediate success than text prompters on P1 (OR = 0.50) and P2 (OR = 0.43). → rq1-logistic

Evidence¶

rq1-logistic¶

Kaitlin Riegel, Yan Cathy Hua, Paul Denny, Victor-Alexandru Pădurean, Juho Leinonen, James Prather, and Adish Singla. 2026. Say What? Examining Text and Voice Input Modalities for Prompt-Based Programming in Computing Education. Proceedings of the 31st ACM Conference on Innovation and Technology in Computer Science Education V. 1 (ITiCSE 2026). https://doi.org/10.1145/3803400.3809397

q3 · i? · associational · r2

Binary logistic regressions across problems P1 and P2 in an introductory C programming course lab examined initial prompt method's effect on immediate success. Unedited voice prompting showed "lower odds of immediate success" versus text, with OR𝑃1 = 0.50 (p= 0.02) and OR𝑃2 = 0.43 (p= 0.01).

"Compared totextprompting, students who initially used uneditedvoice prompting had lower odds of immediate success (OR𝑃1 = 0.50, 95% CI [0.27, 0.89],p= 0.02; OR 𝑃 2= 0.43, 95% CI [0.23, 0.83],p= 0.01)"

Discussion¶

Related Claims¶

• Edited voice prompts did not significantly differ from text prompts in first-attempt success — related
• Initial prompting method did not explain immediate success on the third problem (P3) — related
• Students overwhelmingly used text prompting, and prior modality choice did not predict subsequent choice among dual-mode users — related
• Greater proportion of voice prompts used correlates moderately with greater stated preference for voice — related
• Students perceived text input as superior for accuracy, control, and editability, with transcription errors a key voice drawback — related