The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions

TL;DR

This study investigates how the linguistic expression of personality in conversational agents influences user perceptions and decisions, revealing nuanced effects on trust, emotional response, and charitable giving.

Contribution

It provides empirical evidence on how different linguistic personality cues in CAs affect user perceptions and donation behavior, highlighting potential manipulation risks.

Findings

Pessimistic CAs lowered emotional state and affinity.

Perceptions of trust and competence predicted donations.

CA personality did not directly influence donation decisions.

Abstract

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.