EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Can LLM-driven synthetic participants help user research? A case study in designing augmented reality for education

Suyi Xu, Rafael Roberto, Manoela Silva, Ziwei Gao, Qi Liu

Proceedings of the Design Society · 2026-08 · 6 · 2601-2610

DOI: 10.1017/pds.2026.10618 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Design Society, online erschienen am 02.07.2026. Verfasst von Suyi Xu und 4 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional user research with human participants faces significant challenges, including substantial time and resource requirements, and limited scalability. In response, this study presents an efficient, cost-effective workflow driven by large language models (LLMs) for simulating user research with synthetic participants (SPs) at scale. In a case study in design augmented reality for education, SPs’ open-ended answers were plausible and comprehensive, yet semi-open and closed items diverged from those of humans. SPs can augment early qualitative work, but cannot replace human studies.

Zitieren

APA

Xu, S., Roberto, R., Silva, M., Gao, Z., & Liu, Q. (2026). Can LLM-driven synthetic participants help user research? A case study in designing augmented reality for education. Proceedings of the Design Society, 6, 2601-2610. https://doi.org/10.1017/pds.2026.10618

Vancouver

Xu S, Roberto R, Silva M, Gao Z, Liu Q. Can LLM-driven synthetic participants help user research? A case study in designing augmented reality for education. Proceedings of the Design Society. 2026;6:2601-2610. doi:10.1017/pds.2026.10618

BibTeX
@article{Xu2026,
  author = {Xu, Suyi and Roberto, Rafael and Silva, Manoela and Gao, Ziwei and Liu, Qi},
  title = {Can LLM-driven synthetic participants help user research? A case study in designing augmented reality for education},
  journal = {Proceedings of the Design Society},
  year = {2026},
  volume = {6},
  pages = {2601--2610},
  doi = {10.1017/pds.2026.10618}
}
Kostenlos starten →