Toward Metaphor-Fluid Conversation Design for Voice User Interfaces
Year: 2026
Type: conference-paper
Abstract: Metaphors play a critical role in shaping user experiences with Voice User Interfaces (VUIs), yet existing designs rely on static, human-centric metaphors that fail to adapt to diverse contexts and user needs. We introduce Metaphor-Fluid Design, a novel approach that adjusts metaphorical representations based on conversational use-contexts. We compare this to a Default VUI, which models commercial VUIs commonly designed around the assistant persona, offering uniform interaction across contexts. In Study 1 (N=130), metaphors were mapped to four key use-contexts—commands, information seeking, sociality, and error recovery—along dimensions of formality and hierarchy, revealing distinct preferences for task-specific metaphorical designs. Study 2 (N=91) evaluates a Metaphor-Fluid VUI against a Default VUI, showing that Metaphor-Fluid Design enhances perceived intention to adopt, enjoyment, and likability. However, individual differences in metaphor preferences highlight the need for personalization. These findings challenge the one-size-fits-all paradigm and demonstrate Metaphor-Fluid Design’s potential for more adaptive human-AI interactions.
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4407719098