Reproduce “AI Telephone Surveying: Automating Quantitative Data Collection with an AI Interviewer” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Danny D. Leybzon, Shreyas Tirumala, Nishant Jain, Summer Gillen, Michael Jackson, Cameron McPhee, Jennifer Schmidt
VKL Research, Inc. and SSRS demonstrated an AI interviewer's capability to conduct structured quantitative telephone surveys, achieving a 43% completion rate and an 86% neutral-to-positive respondent experience rating in its refined version, indicating its ability to handle complex survey instruments.
Key insights
- Targeted technical improvements to the AI system's understanding, voice quality, and navigation substantially increased continuation and completion rates, demonstrating the direct impact of AI quality on user engagement.
- Survey length impacts subjective respondent experience, with shorter surveys leading to significantly more positive feedback despite similar completion rates among those who finished.
- Most respondents reported feeling equally or more comfortable discussing sensitive topics with the AI interviewer compared to a human, suggesting AI's potential to mitigate social desirability bias.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.