Population-Scale Network Embeddings Expose Educational Divides in Network Structure Related to Right-Wing Populist Voting

2025-08-28

AI Summary

This study investigates how educational disparities shape right-wing populist voting through social network structure. Leveraging a nationwide population-scale network from the Netherlands, we construct a multiplex social network encompassing five relational contexts: neighborhood, workplace, family, residential proximity, and education. We propose an interpretable group-size-aware network embedding method that employs sparse orthogonalization to learn individual-level embeddings. Results reveal a significant structural association between the education-related dimension—particularly the absence of weak ties across educational strata—and right-wing populist voting. Embedding features alone achieve higher out-of-sample prediction accuracy than conventional individual-level covariates; performance further improves when combined with education level and other controls. To our knowledge, this is the first study to empirically demonstrate the political consequences of educational segregation within a macro-level population network, offering novel relational-structural evidence for understanding political polarization.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Application Domains: Humanities & Computational Social Science
• Humans and AI: Voting

Application Category

• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization
• Economics, Online Markets and Human Computation: Social networks and social learning
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Administrative registry data can be used to construct population-scale networks whose ties reflect shared social contexts between persons. With machine learning, such networks can be encoded into numerical representations -- embeddings -- that automatically capture individuals' position within the network. We created embeddings for all persons in the Dutch population from a population-scale network that represents five shared contexts: neighborhood, work, family, household, and school. To assess the informativeness of these embeddings, we used them to predict right-wing populist voting. Embeddings alone predicted right-wing populist voting above chance-level but performed worse than individual characteristics. Combining the best subset of embeddings with individual characteristics only slightly improved predictions. However, after transforming the embeddings to make their dimensions more sparse and orthogonal, we found that one embedding dimension was strongly associated with the outcome. Mapping this dimension back to the population network revealed differences in network structure related to right-wing populist voting between different school ties and achieved education levels. Our study contributes methodologically by demonstrating how population-scale network embeddings can be made interpretable, and substantively by linking structural network differences in education to right-wing populist voting.

Problem

• Predicting right-wing populist voting using network embeddings
• Interpreting population-scale network structures related to education
• Linking educational network divides to political voting patterns

Innovation

• Used administrative registry data to construct population-scale networks
• Applied machine learning to create network embeddings capturing social contexts
• Transformed embeddings for interpretability, revealing educational divides