Rewarding Engagement and Personalization in Popularity-Based Rankings Amplifies Extremism and Polarization

2025-10-28

AI Summary

This study investigates how online platform ranking algorithms exacerbate political extremism and opinion polarization. Addressing empirically grounded constraints—including positional bias, homophily in user preferences, heightened engagement by ideologically extreme users, and algorithmic reliance on popularity-based ranking—we propose a dynamic agent-based model integrating activity incentives with personalized recommendation. The model is validated through large-scale numerical simulations and a closed-loop online experiment involving hundreds of participants. We formally prove, for the first time, that augmenting popularity-based ranking with explicit rewards for active interaction and personalized content distribution inevitably drives users toward increasingly extreme and polarized content. Results demonstrate a significant increase in exposure to extremist content and heightened intergroup ideological segregation, revealing the structural influence of algorithmic design on societal belief evolution.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences
• Game Theory and Economic Paradigms: Mechanism Design

Application Category

• User Modeling, Personalization and Recommendation: Personalized content ranking and presentation
• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Despite extensive research, the mechanisms through which online platforms shape extremism and polarization remain poorly understood. We identify and test a mechanism, grounded in empirical evidence, that explains how ranking algorithms can amplify both phenomena. This mechanism is based on well-documented assumptions: (i) users exhibit position bias and tend to prefer items displayed higher in the ranking, (ii) users prefer like-minded content, (iii) users with more extreme views are more likely to engage actively, and (iv) ranking algorithms are popularity-based, assigning higher positions to items that attract more clicks. Under these conditions, when platforms additionally reward emph{active} engagement and implement emph{personalized} rankings, users are inevitably driven toward more extremist and polarized news consumption. We formalize this mechanism in a dynamical model, which we evaluate by means of simulations and interactive experiments with hundreds of human participants, where the rankings are updated dynamically in response to user activity.

Problem

• How popularity-based ranking algorithms amplify extremism and polarization
• How rewarding active engagement drives users toward extremist content
• How personalized rankings contribute to polarized news consumption patterns

Innovation

• Rewarding active engagement in popularity-based rankings
• Implementing personalized ranking algorithms for users
• Using dynamical model with simulations and experiments