Students reported text supports structured, iterative planning while some valued voice for getting initial ideas out¶

Claim · All claims
Evidence · 2 studies · 2 qualitative r2 · q2
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Students frequently reported text input helped them structure cohesive thoughts and engage in non-linear problem-solving. → planning q2 i? Some students thought voice input served a valuable role in prompt construction, often to get initial ideas out. → voice-ideas

Evidence¶

planning¶

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

q2 · i? · qualitative · r2

In the qualitative ABSA analysis of reflections, the Planning & Thinking Process category was strongly positive for text (44 positive vs 1 negative) and mixed for voice (6 positive vs 17 negative); students referenced "the opportunity to structure cohesive thoughts" using text inputs.

"Students frequently referenced the opportunity to structure cohesive thoughts or the ability to engage in non-linear problem-solving using text inputs"

voice-ideas¶

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

q2 · i? · qualitative · r2

The qualitative analysis also found "some students thought voice input served a valuable role in their prompt construction – often to get initial ideas out", with one student reporting voice made it easier to think about what the code needed to do.

"some students thought voice input served a valuable role in their prompt construction – often to get initial ideas out"

Discussion¶

Related Claims¶

• Students reported mixed, task-dependent perceptions of the efficiency and speed of voice versus text input — related
• Synchronous AI suggestions shape subsequent writing, offering new ideas but risking influence over the writer's voice and argument — related
• Planning-stage AI ideas were often redundant with or rejected in favor of writers' own ideas: idea attribution was 17.8% among users versus 2.9% among non-users, but ownership did not differ between users and non-users within ai plan. — related
• Students overwhelmingly used text prompting, and prior modality choice did not predict subsequent choice among dual-mode users — related