The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions
This research addresses the risk of manipulation by conversational agents for users in decision-making contexts, though it is incremental in exploring specific linguistic aspects.
The study investigated how conversational agents' linguistic expressions of personality affect user decisions and perceptions in charitable giving, finding that while personality did not alter donation decisions, it influenced perceptions and emotional responses, with pessimistic agents leading to lower emotional states and affinity but higher donations.
Large Language Model-powered conversational agents (CAs) are increasingly capable of projecting sophisticated personalities through language, but how these projections affect users is unclear. We thus examine how CA personalities expressed linguistically affect user decisions and perceptions in the context of charitable giving. In a crowdsourced study, 360 participants interacted with one of eight CAs, each projecting a personality composed of three linguistic aspects: attitude (optimistic/pessimistic), authority (authoritative/submissive), and reasoning (emotional/rational). While the CA's composite personality did not affect participants' decisions, it did affect their perceptions and emotional responses. Particularly, participants interacting with pessimistic CAs felt lower emotional state and lower affinity towards the cause, perceived the CA as less trustworthy and less competent, and yet tended to donate more toward the charity. Perceptions of trust, competence, and situational empathy significantly predicted donation decisions. Our findings emphasize the risks CAs pose as instruments of manipulation, subtly influencing user perceptions and decisions.