User politics and traits influence AI bias in online debates
User Attributes and Political Ideology Shape LLM Receptiveness in Online Political Debates
Artificial IntelligenceComputation and Language
Summary
In online political talks, people now use AI language models (LLMs) to check facts and settle arguments. The researchers found that these AI systems tend to agree more with left-leaning users than right-leaning ones, even when both sides say the same thing. This bias stays even when people debate directly with each other. The AI’s willingness to listen also grows as users talk more, and can change if the AI is trained on different political texts.
What this means in practice
- •For social media platform engineers: Detect and mitigate AI biases in moderation tools to ensure balanced treatment of political viewpoints in online discussions.
- •For political campaign communication teams: Adjust AI-generated messaging strategies based on model receptiveness differences linked to political orientation to improve audience engagement.
Authors
Akram Elbouanani, Yousra Taleb, Gianluca Demartini, Adrian Popescu
Abstract
Online political discussions increasingly involve AI-mediated participation, as users invoke LLMs to assess contested claims, arbitrate disputes, and respond to opposing viewpoints. As these systems become participants in online exchanges, they may alter which speakers and argumentative strategies receive validation within the discussion. We study this interactional dimension by reconstructing 5,376 Debate.org debates as LLM conversations and running nearly 150,000 controlled multi-turn conversations that vary user political orientation, expertise, rhetorical strategy, and defended position, including conversations with competing users. Across naturalistic and controlled debates, we find that LLMs are systematically more receptive to left-leaning than right-leaning users. The asymmetry persists when users with different political orientations defend the same position and when opposing users appear in the same conversation, indicating that it is not fully explained by stance agreement or simple accommodation to the current speaker. Repeated interaction increases receptiveness without eliminating this ordering; expertise also matters, while rhetorical differences are smaller. The pattern appears across multiple models, but is not fixed: fine-tuning on different political corpora can largely erase or reverse it. These results show that LLMs can respond systematically differently to participants in the same political debate, making such interactional asymmetries important for understanding their emerging role in online public discourse.