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

TL;DR

This paper analyzes state and geopolitical censorship on Twitter (X), quantifying its effects on user engagement and developing a classifier to predict account withholding based on content and metadata.

Contribution

It provides the first quantitative analysis of content withholding impacts and introduces a transformer-based model to predict censorship likelihood.

Findings

Censorship reduces likes and retweets by 25% and follower growth by 90%.

Russian accounts outside censorship regions continue to grow.

Content features are most predictive of censorship.

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.