CreepyCoCreator? Investigating AI Representation Modes for 3D Object Co-Creation in Virtual Reality
LMU Munich
How they used Delve
Researchers at LMU Munich, Saarland University, TU Darmstadt and the University of Copenhagen used Delve to inductively code 16 semi-structured interview transcripts from a virtual-reality Wizard-of-Oz study of human-AI co-creation, double-coding half the transcripts before building four themes with Braun and Clarke's thematic analysis.
“The two authors first familiarized themselves with the data by reading the transcripts. We used Delvetool [...] for coding the data. In the first analysis step, both authors read the same subset of transcripts (8 transcripts/50%) separately and created initial codes inductively.”
- Field
- Virtual reality / human-AI co-creation
- Data
- Semi-structured exit interviews with 16 VR study participants (aged 20-30), conducted in a mix of English and German and analysed from audio transcripts
- Approach
- Braun and Clarke's (2006) step-by-step thematic analysis of exit interviews, alongside a 2x2x2 within-subjects Wizard-of-Oz VR experiment analysed with repeated-measures ANOVA
- Data types
- Interviews
Abstract
Generative AI in Virtual Reality offers the potential for collaborative object-building, yet challenges remain in aligning AI contributions with user expectations. In particular, users often struggle to understand and collaborate with AI when its actions are not transparently represented. This paper thus explores the co-creative object-building process through a Wizard-of-Oz study, focusing on how AI can effectively convey its intent to users during object customization in Virtual Reality. Inspired by human-to-human collaboration, we focus on three representation modes: the presence of an embodied avatar, whether the AI’s contributions are visualized immediately or incrementally, and whether the areas modified are highlighted in advance. The findings provide insights into how these factors affect user perception and interaction with object-generating AI tools in Virtual Reality as well as satisfaction and ownership of the created objects. The results offer design implications for co-creative world-building systems, aiming to foster more effective and satisfying collaborations between humans and AI in Virtual Reality.
Citation
Julian Rasch, Julia Töws, Teresa Hirzle, Florian Müller, Martin Schmitz (2025). CreepyCoCreator? Investigating AI Representation Modes for 3D Object Co-Creation in Virtual Reality. CHI Conference on Human Factors in Computing Systems (CHI '25). https://doi.org/10.1145/3706598.3713720