Toward AI-Mediated Avatar-Based Telecommunication: Investigating Visual Impression of Switching Between User- and AI-Controlled Avatars in Video Chat

Telecommunications technology has evolved rapidly, creating opportunities to diversify the communication culture through AI mediation. We anticipate that people will interchangeably use both user-controlled (controlled by transferring user movements) and AI-controlled avatars (controlled autonomously) in everyday communication. For example, users may temporarily use the AI-controlled mode during distractions. This paper argues the importance of investigating the auto-switching between user- and AI-controlled modes to improve the user experience in upcoming AI-mediated telecommunications. As a first step, we conducted a crowdsourced user experiment in a video chat context, focusing on the visual impressions of the displayed avatars. The result shows that impression improved when an appropriate switch setting is used, underscoring the value of this research direction. To identify the appropriate switch setting for our experiment, we developed a general-purpose adaptive experimental design tool based on Bayesian optimization, which we plan to release publicly.