Partial Mobilization: Tracking Multilingual Information Flows Amongst Russian Media Outlets and Telegram

TL;DR

The paper investigates how Russian state media and Telegram channels exchanged and propagated information during 2022, addressing the gap in understanding cross-platform diffusion of narratives. It deploys a scalable pipeline using multilingual MPNet embeddings, DP-Means clustering, and Hawkes processes to quantify topic-level flows between 16 websites and 732 Telegram channels. Key findings show substantial cross-platform sharing, with 33.2% of Telegram topics originating on Russian websites and notable proportions of content circulating from Telegram back to websites; certain sites and channels act as rapid spreaders. The work demonstrates that Telegram functions both as a distribution channel and as a content source for Russian media, offering a scalable methodology for monitoring misinformation and identifying propagandistic channels across multi-language and multi-platform landscapes.

Abstract

In response to disinformation and propaganda from Russian online media following the invasion of Ukraine, Russian media outlets such as Russia Today and Sputnik News were banned throughout Europe. To maintain viewership, many of these Russian outlets began to heavily promote their content on messaging services like Telegram. In this work, we study how 16 Russian media outlets interacted with and utilized 732 Telegram channels throughout 2022. Leveraging the foundational model MPNet, DP-means clustering, and Hawkes processes, we trace how narratives spread between news sites and Telegram channels. We show that news outlets not only propagate existing narratives through Telegram but that they source material from the messaging platform. For example, across the websites in our study, between 2.3% (ura.news) and 26.7% (ukraina.ru) of articles discussed content that originated/resulted from activity on Telegram. Finally, tracking the spread of individual topics, we measure the rate at which news outlets and Telegram channels disseminate content within the Russian media ecosystem, finding that websites like ura.news and Telegram channels such as @genshab are the most effective at disseminating their content.

Figures (7)

• Figure 1: Following, the Russian invasion of Ukraine, the number of Telegram posts in our set of 732 channels spiked from an average of 6,500 to over 27,500. Similarly, our set of Russian websites began to utilize Western media sites like Twitter less often while increasing their use of Telegram (Telegram links increased from 4% of these websites' external hyperlinks to nearly 10%). Our set of Telegram channels themselves began to steadily use platforms like YouTube less often.
• Figure 2: Similarity matrix between our considered websites. Ukraina.ru and newfront.info have the highest similarity with one another. All Russian websites have a high content similarity with the collective messages posted to our set of 732 Telegrams. The three US-based websites have high similarities amongst themselves.
• Figure 3: Propaganda image from @rossiyaneevropa. @rossiyaneevropa argues NATO cannot criticize Russia's activities in Ukraine given the West's war crimes in Libya.
• Figure 4: We report the percentage of each platform's content that was estimated (using the methodology outlined in Section \ref{['sec:methoddology']}) to have been influenced by another platform.
• Figure 5: We report the estimated efficiency (using the methodology outlined in Section \ref{['sec:methoddology']}) of each platform in getting their content onto different platforms.