Can AI Conduct Research Interviews? A 2026 Field Study
Qualitati Research Team · 2026-07-31 · 8 min read
Can AI conduct real research interviews? A 2026 study by Wuttke and colleagues ran AI-led conversational interviews with 571 respondents on migration attitudes and found that AI interviews surfaced reasoning that standardized surveys miss — and that participants rated the AI interview at or above the survey. AI interviewing works, but the delivery mode matters a lot.
What did the study test?
The researchers tested whether a large language model can run open-ended, semi-structured interviews at survey scale. In their paper AI Conversational Interviewing: Scaling Up Semi-Structured and In-depth Interviews (Wuttke, Lang, Klamm, Würschinger & Kreuter, 2026), respondents from the Prolific and Payback panels were interviewed about migration policy by an AI moderator, then completed a matching standardized survey so the two data-collection methods could be compared head to head.
Crucially, the study was designed around a long-standing tension in research: the trade-off between depth and scale. In-depth human interviews are rich but slow and expensive; surveys scale but flatten nuance. The question was whether an AI interviewer could deliver some of the depth of a qualitative interview while keeping the reach of a survey.
How was the AI interviewer built?
According to Wuttke et al. (2026), the text-based interviewer ran on OpenAI's GPT-4o (model gpt-4o-2024-11-20, temperature 0.8), and the voice-based interviewer used OpenAI's GPT Realtime model (gpt-realtime-2025-08-28, temperature 0.7). Notably, the team reported that switching the text interviewer to GPT-5 caused a "marked deterioration in interviewer performance" — a useful reminder that a newer model is not automatically a better interviewer.
Respondents were randomly assigned across three conditions:
- Voice — spoken conversation with the AI.
- Text/chat — typed conversation.
- Free choice — respondents picked their preferred mode.
Of 1,039 respondents initially assigned (with no significant imbalance across conditions, χ²(2)=3.67, p=0.159), the final analytic sample was N=571 with complete interviews linked to survey records.
Voice vs. text: which produces richer interviews?
Voice interviews produced substantially more content. According to Wuttke et al. (2026), the numbers break down as follows:
| Metric | Voice interview | Text interview |
|---|
| Mean words per respondent | 608.8 | 299.8 |
| Mean session length | 8.3 min | 11.5 min |
| Speaking/typing rate | 52.5 words/min | 21.1 words/min |
In short, voice interviews generated roughly twice as many words as text interviews and did so faster, because speaking is quicker than typing. But there is a catch: attrition was concentrated in the voice-only condition, and when respondents were free to choose, they "overwhelmingly selected the chat modality." The authors attribute the voice drop-off to "addressable imperfections" in their implementation rather than a fundamental limit of voice interviewing — a signal that voice UX, not the concept, is the bottleneck.
How did participants rate the AI interview?
Positively. Among respondents who completed the interview, evaluations of the AI interview were at or above those of the standardized survey across all modes (Wuttke et al., 2026). That matters because a common objection to AI interviewing is that it will feel cold or frustrating; here, the completers preferred it to the familiar survey format. The open question the study leaves is completion, not satisfaction: getting people to finish — especially in voice — is where the design work remains.
What did AI interviews reveal that surveys did not?
The headline methodological finding: conversational transcripts exposed "considerations and reasoning that a comprehensive standardized battery does not capture." The AI interviews surfaced markedly different mental models of migration among respondents who had similar attitude scores on the survey. Two people can click the same point on a 7-point scale for completely different reasons — and only the open-ended conversation makes that visible. This is the core argument for AI interviewing: it recovers the "why" behind the number without abandoning scale.
What this means for researchers
For academic, UX, and market researchers, three practical takeaways stand out:
- AI interviewing is a real method now, not a demo. A 571-person study with linked survey data is a serious validation of the approach for opinion and experience research.
- Mode is a design decision. Voice yields richer, longer answers but higher drop-off; chat is what people default to when given the choice. Offering both — and investing in voice UX — is the pragmatic path.
- Use interviews to explain your survey, not just replace it. The biggest payoff was uncovering divergent reasoning behind identical survey scores. Pair a short survey with an AI interview to get both the distribution and the mechanism.
If you want to run this kind of study, QualiTaTi's AI Interviewer conducts voice or text interviews at scale and transcribes them automatically, and ThemeLens can then code the resulting transcripts for themes — turning the "why" the study describes into structured analysis.
Frequently asked questions
Can AI replace human interviewers in qualitative research?
Not wholesale, but it can scale interviewing dramatically. The 2026 study shows AI-led interviews capture reasoning surveys miss and are rated favorably by participants, making them a strong fit for large-N opinion and experience research where recruiting human interviewers would be impractical.
Are voice or text AI interviews better?
They serve different goals. Voice produced about twice the word count (608.8 vs. 299.8 words) and faster responses, but had higher attrition; text is what most respondents chose when free to decide. For maximum richness, use voice with strong UX; for completion and comfort, offer chat.
Which AI model did the study use?
The text interviewer used OpenAI's GPT-4o and the voice interviewer used OpenAI's GPT Realtime model. The authors found GPT-4o outperformed GPT-5 for the interviewing task, showing that model choice should be validated, not assumed.
Do AI interviews really add value over surveys?
Yes — the study found respondents with identical survey attitude scores held substantively different underlying mental models that only the conversational data revealed. AI interviews recover the reasoning behind the numbers.
Primary source: Wuttke, A., Lang, M. M., Klamm, C., Würschinger, Q., & Kreuter, F. (2026). AI Conversational Interviewing: Scaling Up Semi-Structured and In-depth Interviews. arXiv:2606.20064.
Last updated: July 31, 2026. This article is an independent editorial summary of third-party research and is not affiliated with or endorsed by the study's authors.