Artificial Intelligence and Persuasion: A Construal-Level Account

TLDR

More people rely on information from nonhuman agents such as AI and robots, yet little research has examined how persuasion by these agents differs from human persuasion. The study posits that individuals will perceive artificial agents at a low level of construal because of their lack of autonomous goals and intentions. This perspective is grounded in construal‑level theory, which suggests that such perceptions shift focus to how agents implement actions to serve humans rather than why they do so. Across 1,668 participants in multiple studies, we found that construal‑based differences influence compliance with persuasive messages from artificial agents, that messages featuring low‑level construal features are more appropriate and effective, and that these effects are moderated by the agent’s capacity to independently learn from its environment, challenging people’s lay theories.

Abstract

Although more individuals are relying on information provided by nonhuman agents, such as artificial intelligence and robots, little research has examined how persuasion attempts made by nonhuman agents might differ from persuasion attempts made by human agents. Drawing on construal-level theory, we posited that individuals would perceive artificial agents at a low level of construal because of the agents’ lack of autonomous goals and intentions, which directs individuals’ focus toward how these agents implement actions to serve humans rather than why they do so. Across multiple studies (total N = 1,668), we showed that these construal-based differences affect compliance with persuasive messages made by artificial agents. These messages are more appropriate and effective when the message represents low-level as opposed to high-level construal features. These effects were moderated by the extent to which an artificial agent could independently learn from its environment, given that learning defies people’s lay theories about artificial agents.