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

In response to disinformation and propaganda from Russian online media following the Russian invasion of Ukraine, Russian outlets including Russia Today and Sputnik News were banned throughout Europe. Many of these Russian outlets, in order to reach their audiences, began to heavily promote their content on messaging services like Telegram. In this work, we study how 16~Russian media outlets have interacted with and utilized 732~Telegram channels throughout 2022. To do this, we utilize a multilingual version of the foundational model MPNet to embed articles and Telegram messages in shared embedding space and semantically compare content. Leveraging a parallelized version of DP-Means clustering, we perform paragraph-level topic/narrative extraction and time-series analysis with Hawkes Process. With this approach, across our websites, we find between 2.3\% (ura.news) and 26.7\% (ukraina.ru) of content resulted from activity on Telegram. Finally, tracking the spread of individual narratives, we measure the rate at which these websites and channels disseminate content in the Russian media ecosystem.