Back to Search
Start Over
Conversation-based hybrid UI for the repertory grid technique: A lab experiment into automation of qualitative surveys.
- Source :
-
International Journal of Human-Computer Studies . Apr2024, Vol. 184, pN.PAG-N.PAG. 1p. - Publication Year :
- 2024
-
Abstract
- A frequent use of conversational user interfaces (CUIs) today is improving the users' experience with online quantitative surveys. In this paper, we explore the use of CUIs in qualitative surveys. As a concrete use case, we adopt a specific, well-structured, qualitative research method called the repertory grid technique (RGT). We developed a hybrid user interface (HUI) that combines a graphical user interface (GUI) with a CUI to automate the distinct stages in a RGT survey. A pilot study was used to verify the feasibility of the approach and to fine-tune interface aspects of an initial prototype. In this paper, we report the results of a within-subject lab experiment with 24 participants that aimed to establish the performance and UX in a realistic context of a more advanced prototype. We observed a small decrease in UX in some hedonistic aspects, but also confirmed that the HUI performs similarly to a human agent in most pragmatic aspects. These results provide support for our hypothesis that automating qualitative surveys is possible with proper interface design. We hope that our work can inspire other researchers to design additional tools for qualitative survey automation, especially now that generative AI systems, such as ChatGPT, open up interesting new ways for computer systems to interact with users in natural language. [Display omitted] • Explored CUIs in qualitative survey automation, focusing on RGT methodology. • Developed HUI integrating GUI and CUI for experimenting RGT automation. • Conducted lab experiment with 24 participants for the HUI idea evaluation. • The HUI prototype showed UX decrease in hedonism, yet matched human agents pragmatically. • Our findings support AI-driven qualitative survey automation potential. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10715819
- Volume :
- 184
- Database :
- Academic Search Index
- Journal :
- International Journal of Human-Computer Studies
- Publication Type :
- Academic Journal
- Accession number :
- 175136509
- Full Text :
- https://doi.org/10.1016/j.ijhcs.2024.103227