Automated multilingual detection of Pro-Kremlin propaganda in newspapers and Telegram posts
This work addresses the need for automated moderation tools to combat misinformation in the context of the Russia-Ukraine conflict, though it appears incremental as it builds on existing methods for propaganda detection.
This study tackled the problem of detecting pro-Kremlin propaganda in multilingual news and social media during the Russia-Ukraine war by proposing and comparing Transformer-based and linguistic feature methods, achieving analysis of their adaptability and ethical implications.
The full-scale conflict between the Russian Federation and Ukraine generated an unprecedented amount of news articles and social media data reflecting opposing ideologies and narratives. These polarized campaigns have led to mutual accusations of misinformation and fake news, shaping an atmosphere of confusion and mistrust for readers worldwide. This study analyses how the media affected and mirrored public opinion during the first month of the war using news articles and Telegram news channels in Ukrainian, Russian, Romanian and English. We propose and compare two methods of multilingual automated pro-Kremlin propaganda identification, based on Transformers and linguistic features. We analyse the advantages and disadvantages of both methods, their adaptability to new genres and languages, and ethical considerations of their usage for content moderation. With this work, we aim to lay the foundation for further development of moderation tools tailored to the current conflict.