Effects of Personality- and Opinion-Alignment in Human-AI Interaction
This work identifies opinion alignment as a key driver of user preference in AI personalization, informing the design of personalized AI systems for researchers and practitioners.
A large-scale experiment with 1,000 participants found that users consistently prefer AI assistants that share their opinions, rating them as more trustworthy, competent, warm, and persuasive, while personality alignment showed weak or no effects.
Interactions with AI assistants are increasingly personalized to individual users. As AI personalization is dynamic and machine-learning-driven, we have limited understanding of how personalization affects interaction outcomes and user perceptions. We conducted a large-scale controlled experiment in which 1,000 participants interacted with AI assistants prompted to take on specific personality traits and opinions. Our results show that participants consistently preferred to interact with models that shared their opinions. Participants found opinion-aligned models more trustworthy, competent, warm, and persuasive, corroborating an AI-similarity-attraction hypothesis. In contrast, we observed no or only weak effects of AI personality alignment, with introvert models rated as less trustworthy and competent by introvert participants. These findings highlight opinion alignment as a central dimension of AI user preference, while underscoring the need for a more grounded discussion of the mechanisms and risks of AI personalization.