Recommendation algorithms increase opinion polarization in social networks
Polarization Dynamics under Algorithmic Recommendations in LLM-based Online Social Networks
Social and Information Networks
Summary
People often wonder if online algorithms that suggest posts or new friends make opinions more divided. The authors used AI chatbots to simulate a social network where these recommendations happen in two ways: suggesting new friends or showing more posts. They found that both methods made users’ opinions more extreme and spread out than if no recommendations were given. This suggests recommendation systems can contribute to forming stronger, more polarized beliefs online.
What this means in practice
- •For social media platform engineers: Design recommendation features that anticipate how exposure and new connections influence opinion division among users.
- •For online community moderators: Develop moderation strategies informed by how different recommendation styles may increase polarization and extreme opinions.
Tested on simulated data.
Authors
Ali Safarpoor Dehkordi, Mohammad Shirzadi, Mehwish Nasim, Ahad N. Zehmakan
Abstract
How do recommendation algorithms contribute to the formation of polarized opinions in online social networks? This question has been studied through empirical analyses of real platforms and mathematical models of opinion dynamics. Empirical studies capture user behavior but are often limited by noisy, incomplete, or inaccessible platform data, while mathematical models offer control and interpretability but usually rely on simplified opinion update rules. More recently, large language model (LLM)-based social simulations have provided an alternative for studying recommendation and opinion dynamics through natural-language interactions. However, how different ways of applying recommendations shape opinion dynamics remains underexplored. In this work, we provide a controlled comparison of two different recommendation mechanisms in an LLM-based online social network simulation. Edge Recommendation (ER) introduces new connections in the network, while Content-Exposure Recommendation (CR) exposes additional users to individual posts without modifying the underlying graph. Our framework represents users as LLM-based agents who interact in natural language while maintaining evolving opinion states. We measure polarization as opinion dispersion, extremization as the average distance of opinions from the neutral midpoint, and reinforcement as interactions that amplify already aligned opinions. Our results show higher mean polarization and extremization across recommendation conditions compared with the no-recommendation baseline, with absolute differences of up to $0.12$ in our main experiments.