Customizability in conversational agents and their impact on health engagement

Abstract

Conversational agents (CAs) are effective tools for health behavior change, yet little research investigates the mechanisms through which they work. In accordance with the Computer as Social Actors (CASA) paradigm, we suggest that agents are perceived as human-like actors and hence influence behavior much as human coaches might. As such, agents should be designed to resemble ideal interaction patterns—for example, by resembling their users. Our study will test this paradigm by testing the impact of customization on similarity and reciprocity, which in turn are hypothesized to improve perceptions of the agent and compliance with the agent's recommendations.