Quantifying Political Partisanship for Cross-Platform Analyses

2026-07-23

AI Summary

This study addresses the challenge of consistently measuring users’ political leanings across social media platforms, a task hindered by reliance on platform-specific features. To overcome this limitation, the authors propose a text-based, cross-platform framework that leverages AllSides news media bias ratings as an external supervision signal. Within a Transformer-derived sentence embedding space, they construct an interpretable partisan axis and assign political scores to posts via vector projection. This approach enables, for the first time, a comparative analysis of partisan distributions between Bluesky and Truth Social—two ideologically asymmetric platforms. Experiments on 1.3 million posts demonstrate that the derived partisan scores exhibit significant correlation with AllSides ratings both within each platform and on an independent Twitter corpus, revealing fine-grained political dynamics that transcend platform identity.

Abstract

Research on political polarization on social media depends on the ability to reliably measure partisanship in user-generated content. However, existing approaches are typically tailored to platform-specific properties, such as structural affordances or linguistic conventions, which hurts generalizability across platforms. This limitation is increasingly consequential as the social media ecosystem fragments and fringe, alt-tech platforms emerge alongside mainstream ones. We propose a text-based, platform-portable methodology for measuring political partisanship in social media posts, anchored by an external news-credibility signal. Posts are embedded using a transformer-based sentence encoder and clustered into topic groups, which are labeled using the aggregated AllSides media bias scores of cited news outlets. A partisanship axis is then constructed in the embedding space as the difference between centroids of oppositely labeled clusters, and individual posts are scored by projection onto this axis. We apply the method to a corpus of approximately 1.3 million posts collected from Bluesky and Truth Social during the six months preceding the 2024 U.S. presidential election, providing the first cross-platform comparison of partisanship distributions on these two ideologically asymmetric platforms. The resulting partisanship scores correlate significantly with held-out AllSides media bias scores both in-distribution and out-of-distribution on an independent Twitter corpus, and recover within-platform partisan dynamics that platform identity alone cannot explain.

Problem

• political partisanship
• cross-platform analysis
• social media polarization
• platform generalizability
• user-generated content

Innovation

• cross-platform
• political partisanship
• sentence embedding
• media bias
• transformer-based encoding