Preprint
Say What? Examining Text and Voice Input Modalities for Prompt-Based Programming in Computing Education
Kaitlin Riegel et al., arXiv, 2026
Read the originalRead on October 17, 2026
- What it is
- An exploratory study of introductory programming students who solved Prompt Problems by typing or speaking their prompts to a language model. It compares first-attempt success by input method.
- How much weight it carries
- Preprint, submitted July 2026, and not yet a published journal or conference paper. Students solving classroom tasks, so results may not carry over to professional developers.
Facts taken from this source
- In the same 2026 preprint, there was no difference in first-attempt success when students edited their transcribed voice prompts before submitting.
“There was no difference in success rate if students edited their transcribed voice prompts before submission.” (Abstract)
- In a 2026 preprint, students who typed their prompts were more likely than students who submitted unedited voice prompts to succeed on the first attempt, on two of three problems.
“For two of the three problems, we found that students who typed their prompts using text were more likely to have those prompts succeed on the first attempt than students who submitted unedited voice prompts.” (Abstract)