Who Leads in the Shadows? ERGM and Centrality Analysis of Congressional Democrats on Bluesky

2025-07-21

AI Summary

This study investigates how political influence emerges and information propagates among U.S. Congressional Democrats on the decentralized social platform Bluesky—which lacks algorithmic recommendation—challenging assumptions about visibility-driven authority. Methodologically, it integrates social network analysis, exponential random graph modeling (ERGM), and BERTopic-based textual modeling across four data layers: follows, mentions, retweets, and discussion content. Results reveal that non-mainstream legislators frequently occupy structurally central brokerage positions, undermining the “visibility-as-authority” paradigm; intra-party networks exhibit latent hierarchical power structures and pronounced discursive polarization, with systematic differences across factions in issue prioritization and rhetorical style. This work constitutes the first empirical demonstration of self-organizing logic and micro-level power reproduction within partisan networks on algorithm-free platforms, establishing a novel theoretical framework and empirical benchmark for studying digital political communication in the absence of algorithmic curation.

Technology Category

Application Domains: Humanities & Computational Social ScienceData Mining & Knowledge Management: Graph Mining, Social Network Analysis & CommunityNatural Language Processing: Discourse, Pragmatics & Argument Mining

Application Category

Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarizationWeb Mining and Content Analysis: Content-based information diffusionResponsible Web: Algorithmic accountability and transparency on the web

Abstract

Following the 2024 U.S. presidential election, Democratic lawmakers and their supporters increasingly migrated from mainstream social media plat-forms like X (formerly Twitter) to decentralized alternatives such as Bluesky. This study investigates how Congressional Democrats use Bluesky to form networks of influence and disseminate political messaging in a platform environment that lacks algorithmic amplification. We employ a mixed-methods approach that combines social network analysis, expo-nential random graph modeling (ERGM), and transformer-based topic mod-eling (BERTopic) to analyze follows, mentions, reposts, and discourse pat-terns among 182 verified Democratic members of Congress. Our findings show that while party leaders such as Hakeem Jeffries and Elizabeth War-ren dominate visibility metrics, overlooked figures like Marcy Kaptur, Donald Beyer, and Dwight Evans occupy structurally central positions, suggesting latent influence within the digital party ecosystem. ERGM re-sults reveal significant homophily along ideological, state, and leadership lines, with Senate leadership exhibiting lower connectivity. Topic analysis identifies both shared themes (e.g., reproductive rights, foreign conflicts) and subgroup-specific issues, with The Squad showing the most distinct discourse profile. These results demonstrate the potential of decentralized platforms to reshape intra-party communication dynamics and highlight the need for continued computational research on elite political behavior in emerging digital environments.

Problem

• Analyze influence networks of Congressional Democrats on Bluesky
• Examine political messaging without algorithmic amplification
• Identify latent influence and discourse patterns in decentralized platforms

Innovation

• Combines ERGM and BERTopic for network analysis
• Analyzes decentralized platform influence dynamics
• Identifies latent influence via structural centrality