From Information-Seeking to Information-Asking: Designing RefuGPT, a Chatbot for Ukrainian Refugees in Switzerland
Digital Government: Research and Practice · 31.12.2025 · 6 (4) · 1-21
DOI: 10.1145/3735140 ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital Government: Research and Practice, online erschienen am 18.12.2025. Verfasst von Kilian Sprenkamp und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: Digitalization Initiative of the Zurich Higher Education Institutions.
Abstract (Originalsprache)
A key challenge for refugees is accessing relevant information about their host country. However, refugees often face disorientation during their information-seeking process. Disorientation is driven by language barriers, a digital divide, high urgency, and an evolving situation, which hinders the refugees’ ability to access information. Addressing the issue of disorientation, we propose an IT artifact, i.e., a chatbot called RefuGPT , designed through a rigorous Design Science Research Methodology. RefuGPT leverages the power of a large language model (LLM), GPT-4 while accessing two distinct sources of information, i.e., official and community-based information utilizing retrieval augmented generation and prompt-based learning (Figure 1 ). We assess RefuGPT's usefulness and usability through an ex-post evaluation in a naturalistic setting with Ukrainian refugees. Hence, we show that our bi-layered LLM-based chatbot can effectively assist refugees. They thus move from information-seeking to a more effortless information-asking. Based on those insights, we propose design principles as well as practical recommendations for refugee chatbots.
Förderung
- Digitalization Initiative of the Zurich Higher Education Institutions
Zitieren
APA
Sprenkamp, K., Eckhardt, S., Zavolokina, L., & Schwabe, G. (2025). From Information-Seeking to Information-Asking: Designing RefuGPT, a Chatbot for Ukrainian Refugees in Switzerland. Digital Government: Research and Practice, 6(4), 1-21. https://doi.org/10.1145/3735140
Vancouver
Sprenkamp K, Eckhardt S, Zavolokina L, Schwabe G. From Information-Seeking to Information-Asking: Designing RefuGPT, a Chatbot for Ukrainian Refugees in Switzerland. Digital Government: Research and Practice. 2025;6(4):1-21. doi:10.1145/3735140
BibTeX
@article{Sprenkamp2025,
author = {Sprenkamp, Kilian and Eckhardt, Sven and Zavolokina, Liudmila and Schwabe, Gerhard},
title = {From Information-Seeking to Information-Asking: Designing RefuGPT, a Chatbot for Ukrainian Refugees in Switzerland},
journal = {Digital Government: Research and Practice},
year = {2025},
volume = {6},
number = {4},
pages = {1--21},
doi = {10.1145/3735140}
}
EUVIMED