Recommendations that reduce political polarization by adapting to user tolerance
Reversing Polarization through Tolerance-Aware Recommendation and Adaptive Diversification
Social and Information Networks
Summary
Polarization happens when people only hear opinions like their own, making divisions worse. The authors look at ways recommendation systems can not just slow polarization but actually reverse it. They propose a method that learns how much disagreement each person can tolerate and shows more diverse views to extreme opinions while personalizing for moderates. Their tests with simulated and AI-driven agents show this strategy can bring people closer together, even with social pressures and influencers. This approach helps reconnect groups in divided societies by carefully balancing personalized and diverse recommendations.
What this means in practice
- •For social media platform engineers: Design recommendation algorithms that reduce user polarization by adapting content based on individual tolerance levels and opinion extremity.
- •For online community managers: Create moderation and recommendation policies that reconnect divided user groups by balancing personalized and diverse content exposure.
Authors
Zhanzhan Zhao, Shuqi Zhao, Zichen Fan, Dana Randall
Abstract
Recommender systems face a tension between broadening exposure to diverse viewpoints and avoiding interactions that reinforce extreme positions. This tension is especially consequential in already polarized populations. Here we investigate whether recommendation strategies can reverse polarization rather than merely slow its development. Building on the Attraction--Repulsion Model of opinion dynamics, we introduce two complementary design principles: Tolerance-aware recommendation, which seeks to learn each individual's tolerance for disagreement and reduces exposure to viewpoints beyond that tolerance, and adaptive diversification, which broadens exposure for agents with more extreme opinions while retaining stronger personalization for moderates. Agent-based experiments show that highly personalized recommendations intensify polarization under polarized initial conditions. Tolerance awareness alone primarily slows polarization, whereas combining it with adaptive diversification can reduce polarization below its initial level and, under suitable conditions, restore consensus. Additional experiments incorporating persistent extreme influencers and a spiral-of-silence mechanism show that the combined strategy can mitigate polarization under social pressure and selective participation. To examine whether these findings extend beyond predefined opinion-update rules, we repeat the experiments on a simulated social platform populated by 100 LLM-driven agents prompted to move toward opinions similar to their own and away from those that differ substantially. Across three runs, the combined strategy is again the only recommendation policy tested that reverses polarization in every run. These findings distinguish polarization prevention from reversal and identify tolerance-aware, adaptive exposure as a promising recommendation design principle for reconnecting divided populations.