State & Geopolitical Censorship on Twitter (X): Detection & Impact Analysis of Withheld Content

2025-08-18

AI Summary

This study quantifies the impact of national and geopolitical content moderation on user behavior on X (formerly Twitter), focusing on how post-level censorship suppresses posting frequency, engagement (likes/shares), and follower growth. We propose the first user-granularity framework for predicting moderation effects, integrating tweet content, metadata, and user profiling features within a Transformer-based binary classification model augmented with temporal aggregation; it achieves an F1-score of 0.73 and AUC of 0.83. Results demonstrate that moderation significantly reduces local audience engagement—decreasing likes and retweets by 25%—and slashes follower growth rates by 90%. Crucially, we uncover strong heterogeneity in moderation efficacy contingent on audience geographic distribution, revealing that suppression effects are markedly attenuated when audiences are internationally dispersed. This spatially contingent pattern provides novel empirical evidence for understanding geographically differentiated content governance strategies.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Web Mining and Content Analysis: Content-based information diffusion
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization

Abstract

State and geopolitical censorship on Twitter, now X, has been turning into a routine, raising concerns about the boundaries between criminal content and freedom of speech. One such censorship practice, withholding content in a particular state has renewed attention due to Elon Musk's apparent willingness to comply with state demands. In this study, we present the first quantitative analysis of the impact of state censorship by withholding on social media using a dataset in which two prominent patterns emerged: Russian accounts censored in the EU for spreading state-sponsored narratives, and Turkish accounts blocked within Turkey for promoting militant propaganda. We find that censorship has little impact on posting frequency but significantly reduces likes and retweets by 25%, and follower growth by 90%-especially when the censored region aligns with the account's primary audience. Meanwhile, some Russian accounts continue to experience growth as their audience is outside the withholding jurisdictions. We develop a user-level binary classifier with a transformer backbone and temporal aggregation strategies, aiming to predict whether an account is likely to be withheld. Through an ablation study, we find that tweet content is the primary signal in predicting censorship, while tweet metadata and profile features contribute marginally. Our best model achieves an F1 score of 0.73 and an AUC of 0.83. This work informs debates on platform governance, free speech, and digital repression.

Problem

• Analyzing impact of state censorship on social media engagement
• Developing predictive model for identifying accounts subject to withholding
• Investigating effects of content withholding on user metrics

Innovation

• Transformer-based user-level binary classifier
• Temporal aggregation strategies for prediction
• Tweet content as primary censorship signal