Effects of rhetorical strategies and skin tones on agent persuasiveness in assisted decision-making

Abstract

Appearance and linguistic cues may influence how both people and Intelligent Virtual Agents (IVAs) are perceived and evaluated by others; appearance (e.g., skin tone) has been linked to various implicit biases such as agreeing more with stereotypical attractive faces, while particular linguistic cues may effectively increase persuasiveness. In this paper, we report an online study (N=59) evaluating how strategic linguistic cues (expertise: high vs. low) may shape the implicit disadvantages associated with ethnic stereotypes (skin tone: dark vs. light). We found that a virtual agent with a high level of expertise was considered more persuasive, dominant, intelligent, and likeable regardless of their skin tone, and that participants complied more with IVAs with a darker skin tone. Our results suggest that the design of IVAs requires the deliberate considerations of factors such as appearance and linguistic behaviors in order to achieve intended outcomes.