π€ AI Summary
This study addresses the challenges of insufficient social presence and excessive cognitive load in virtual reality (VR)-based requirements discussions. To mitigate these issues, the authors propose a novel approach that integrates real-time speech-to-text conversion with automatically generated user personas, embedding dynamic user profiles into VR stakeholder role-playing scenarios for the first time. By enabling persona-driven interactive requirements elicitation within an immersive environment, the system significantly enhances usersβ sense of social presence and satisfaction with usability while effectively reducing cognitive workload. This work introduces a new human-AI collaborative paradigm for requirements engineering and demonstrates the potential of multimodal technologies to improve collaborative efficiency in immersive settings.
π Abstract
In this study, we propose a novel approach that supports requirements discussions in virtual environments by automatically generating personas from real-time speech-to-text data. In our pilot experiment, 18 participants (14 from universities and 4 from IT companies) used the generated personas to discuss accessibility requirements within the virtual environment. Participants reported a relatively high level of satisfaction with the social presence and usability of the VR system. We also found that requirements discussions based on personas have a lower workload. Finally, we outline the main directions for future work.