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.

In politically charged environments, understanding how ideological narratives emerge, spread, and shape user behavior on social media is critical for applications ranging from misinformation detection to enriching public discourse with verifiable truth. In this study, we present NARRA-SCALE, a framework that brings together network analysis, narrative detection, stance classification, and bipartite scaling to place users, communities, and messages along a single ideological dimension. As a case study, we apply NARRA-SCALE to a U.S. race relations related dataset chiefly polarized between “Black Lives Matter” and “All Lives Matter” supporters. We extract topic coded key phrases and named entities using frequency-based heuristics. Using key phrase co-occurrence relationships and latent representations of matching messages, we mine grouped (entities, issues/aspects, values) triplets characterizing key recurring narratives within the corpus. We use an LLM to summarize messages matching each triplet. Subsequently, a panel of experts label the stance information of the narratives on their key phrases, enabling weak supervision for training a high-accuracy stance detection model which achieves an 81 % F1 score on a held-out gold standard. Next, we construct a signed bipartite graph with colored edges (i.e., representing support versus opposition) between users and key terms mentioned in their messaging corresponding to debated core values, issues, and actors to co-scale their positions on a [-1,+1] range. Our method reaches 91 % agreement with user groups identified through community structure as well as with the “ideal points” of political elites and the general public on Twitter in the U.S. and five European countries.

Many social media studies argue that social media creates echo chambers where some users only interact with peers of the same political orientation. However, recent studies suggest that a substantial amount of Cross-Partisan Interactions (CPIs) do exist --- even within echo chambers, but they may be toxic. There is no consensus about how such interactions occur and when they lead to healthy or toxic dialogue. In this paper, we study a comprehensive Twitter dataset that consists of 3 million tweets from 2020 related to the U.S. context to understand the dynamics behind CPIs. We investigate factors that are more associated with such interactions, including how users engage in CPIs, which topics are more contentious, and what are the stances associated with healthy interactions. We find that CPIs are significantly influenced by the nature of the topics being discussed, with politically charged events acting as strong catalysts. The political discourse and pre-established political views sway how users participate in CPIs, but the direction in which users go is nuanced. While Democrats engage in cross-partisan interactions slightly more frequently, these interactions often involve more negative and nonconstructive stances compared to their intra-party interactions. In contrast, Republicans tend to maintain a more consistent tone across interactions. Although users are more likely to engage in CPIs with popular accounts in general, this is less common among Republicans who often engage in CPIs with accounts with a low number of followers for personal matters. Our study has implications beyond Twitter as identifying topics with low toxicity and high CPI can help highlight potential opportunities for reducing polarization while topics with high toxicity and low CPI may action targeted interventions when moderating harm.

Social media has become an important place for online marketing like never before. Businesses use various techniques to identify and reach potential customers across multiple platforms and deliver a message to grab their attention. A notable post could attract potential customers to the product landing page. However, the acquisition is only the beginning. The landing page should respond to the visitor's need for persuasion to increase conversion rates. Showing every visitor the same page is far from that goal. Even if the product meets everyone's needs, their priorities may differ. In this study, we propose a pipeline that includes gathering and identifying potential customers from Twitter, determining their priorities by understanding the context of their message, and creating a coherent paragraph that addresses the issue to display on the landing page.