Edited voice prompts did not significantly differ from text prompts in first-attempt success¶

Claim · All claims
Evidence · 1 study · associational r1 · q3
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Students who edited their transcribed voice prompts before submission did not significantly differ from text prompters in immediate success on P1 or P2. → edited-voice

Evidence¶

edited-voice¶

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 · r1

The same logistic regression models across P1 and P2 found edited voice prompts "did not significantly differ" from text (OR𝑃1 = 0.57, p= 0.17; OR𝑃2 = 0.72, p= 0.38); confidence intervals cross 1. The authors suggest students who edit voice prompts may be as likely to succeed as text users.

"students whoeditedtheir voice prompts did not significantly differ (OR𝑃 1= 0.57, 95% CI [0.26, 1.27],p= 0.17; OR𝑃 2= 0.72, 95% CI [0.35, 1.49],p= 0.38)"

Discussion¶

Related Claims¶

• Adult ESL learners report above-neutral perceptions of ASR as a writing tool on usefulness, ease of use, and intention to use — the general claim this finding bears on, with the studies behind it
• Unedited voice prompts have lower odds of first-attempt success than text prompts on two of three Prompt Problems — related
• Students perceived text input as superior for accuracy, control, and editability, with transcription errors a key voice drawback — 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
• A substantial share of builders' voiced design intentions never reaches the typed prompt, leaving design choices to the production stack's defaults — related
• Greater proportion of voice prompts used correlates moderately with greater stated preference for voice — related
• Students reported mixed, task-dependent perceptions of the efficiency and speed of voice versus text input — related