Students overwhelmingly used text prompting, and prior modality choice did not predict subsequent choice among dual-mode users¶

Claim · All claims
Evidence · 2 studies · 2 associational r1–r2 · q3
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Of 919 students, 813 (88.5%) used only text prompting, 44 (4.8%) only voice, and 62 (6.7%) both. → usage-counts q3 i? Among the 62 students who attempted both modalities, previous input choice did not significantly influence subsequent modality selection (OR = 1.28, p= 0.41). → persistence-model

Evidence¶

usage-counts¶

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

Log data from the weekly lab (including the warm-up problem) show 813 students used only text (88.5%), 44 only voice (4.8%), and 62 both (6.7%), which the authors describe as "an overwhelming bias towards text prompting".

"there were 813 students who only used text-based prompting (88.5%), 44 who only used voice (4.8%), and 62 who attempted both input methods (6.7%), demonstrating an overwhelming bias towards text prompting"

persistence-model¶

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

A binary mixed-effects logistic regression (random intercept per participant) on the 62 dual-modality students found previous prompt modality did not significantly predict subsequent choice (OR = 1.28, 95% CI [0.71, 2.31], p= 0.41); choices were "independent of their previous choices".

"The effect was not statistically significant (OR = 1.28, 95% CI [0.71, 2.31],p= 0.41), indicating that, for this subset, students’ choices were independent of their previous choices."

Discussion¶

Related Claims¶

• Students reported mixed, task-dependent perceptions of the efficiency and speed of voice versus text input — related
• Edited voice prompts did not significantly differ from text prompts in first-attempt success — related
• Unedited voice prompts have lower odds of first-attempt success than text prompts on two of three Prompt Problems — related
• Students reported text supports structured, iterative planning while some valued voice for getting initial ideas out — related
• Greater proportion of voice prompts used correlates moderately with greater stated preference for voice — related
• Initial prompting method did not explain immediate success on the third problem (P3) — related