Negative Ties Highlight Hidden Extremes in Social Media Polarization

2025-01-09

AI Summary

This study investigates how cross-ideological conflict on social media reveals the structural underpinnings of political polarization and the expression of extremist views. Method: Leveraging signed interaction data (positive/negative votes) from the Spanish social news platform Menéame, we construct a signed network and propose Signed Hamiltonian Eigenvector Embedding for Proximity (SHEEP), integrated with correspondence analysis and signed network modeling. Contribution/Results: Unsigned networks identify only mainstream ideological communities, whereas negative ties precisely locate adversarial extremist users across ideological camps. Far-left users initiate cross-ideological negative interactions more frequently, while far-right users exhibit highly homogeneous negative linking patterns. We provide the first empirical confirmation that negative edges are indispensable for identifying extremist users, uncovering systematic asymmetries in adversarial behavior between left- and right-wing actors. These findings yield novel measurement tools and theoretical insights into political polarization in digital spaces.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization
• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Human interactions in the online world comprise a combination of positive and negative exchanges. These diverse interactions can be captured using signed network representations, where edges take positive or negative weights to indicate the sentiment of the interaction between individuals. Signed networks offer valuable insights into online political polarization by capturing antagonistic interactions and ideological divides on social media platforms. This study analyzes polarization on Men'eame, a Spanish social media that facilitates engagement with news stories through comments and voting. Using a dual-method approach -- Signed Hamiltonian Eigenvector Embedding for Proximity (SHEEP) for signed networks and Correspondence Analysis (CA) for unsigned networks -- we investigate how including negative ties enhances the understanding of structural polarization levels across different conversation topics on the platform. We find that the unsigned Men'eame network accurately delineates ideological communities, but negative ties are necessary for detecting extreme users who engage in antagonistic behaviors. We also show that far-left users are more likely to use negative interactions to engage across ideological lines, while far-right users interact primarily with users similar to themselves.

Problem

• Social Media
• Political Polarization
• Emotional Conflict

Innovation

• Signed Network Analysis
• Political Polarization
• Online Social Interactions