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

2026-02-19

AI Summary

This study investigates how personality traits expressed through language by large language model–driven conversational agents influence users’ perceptions and decisions in charitable donation contexts. Through a crowdsourced experiment (N=360), the research systematically manipulates three linguistic personality dimensions—attitude, authority, and reasoning style—and employs structural equation modeling to analyze their effects on affect, trust, and donation behavior. The work provides the first multidimensional deconstruction of linguistic personality in conversational agents, revealing that while personality traits do not directly determine donations, they indirectly shape behavior through trust, perceived competence, and situational empathy. Notably, pessimistic agents, despite lowering user mood and evaluations, significantly increased donation intent—an unexpected finding that underscores potential manipulative risks and ethical challenges in agent design.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Humans and AI: Learning Human Values and Preferences
• Multiagent Systems: Agent Communication

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

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.

Problem

• conversational agents
• personality expression
• user perception
• charitable giving
• linguistic cues

Innovation

• conversational agents
• personality expression
• linguistic manipulation
• user perception
• large language models