Personality Modeling for Persuasion of Misinformation using AI Agent

2025-01-15

AI Summary

This study investigates how the Big Five personality traits influence individuals’ susceptibility to, willingness to disseminate, and responsiveness to corrections of social media misinformation. Method: Leveraging the AgentScope framework and the GLM-4-Flash large language model, we constructed 90 heterogeneous AI agents—each instantiated with distinct Big Five trait profiles—to simulate persuasive and resistance behaviors across six misinformation topics. Contribution/Results: We identify, for the first time, a non-transitive effect of personality on misinformation engagement: critically oriented personalities achieve highest persuasion success in evidence-based discussions (e.g., 59.4% success rate on HIV-related misinformation), whereas low-aggression intervention strategies maintain stable efficacy (>40%) across diverse personality pairings. Empirical results further demonstrate that trust-building and affective engagement significantly outperform adversarial correction approaches. These findings provide empirically grounded, deployable behavioral models and actionable strategy guidelines for designing personalized anti-misinformation systems.

Technology Category

• Multiagent Systems: Adversarial Agents
• Application Domains: Misinformation & Fake News
• Humans and AI: Learning Human Values and Preferences

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Agentic search

Abstract

The proliferation of misinformation on social media platforms has highlighted the need to understand how individual personality traits influence susceptibility to and propagation of misinformation. This study employs an innovative agent-based modeling approach to investigate the relationship between personality traits and misinformation dynamics. Using six AI agents embodying different dimensions of the Big Five personality traits (Extraversion, Agreeableness, and Neuroticism), we simulated interactions across six diverse misinformation topics. The experiment, implemented through the AgentScope framework using the GLM-4-Flash model, generated 90 unique interactions, revealing complex patterns in how personality combinations affect persuasion and resistance to misinformation. Our findings demonstrate that analytical and critical personality traits enhance effectiveness in evidence-based discussions, while non-aggressive persuasion strategies show unexpected success in misinformation correction. Notably, agents with critical traits achieved a 59.4% success rate in HIV-related misinformation discussions, while those employing non-aggressive approaches maintained consistent persuasion rates above 40% across different personality combinations. The study also revealed a non-transitive pattern in persuasion effectiveness, challenging conventional assumptions about personality-based influence. These results provide crucial insights for developing personality-aware interventions in digital environments and suggest that effective misinformation countermeasures should prioritize emotional connection and trust-building over confrontational approaches. The findings contribute to both theoretical understanding of personality-misinformation dynamics and practical strategies for combating misinformation in social media contexts.

Problem

• Personality Traits
• Fake News Belief
• Social Media Disinformation

Innovation

• AI Agent Simulation
• Critical Thinking Personality
• Persuasion Strategy