Automated Multilingual Detection of Pro-Kremlin Propaganda in Newspapers and Telegram Posts
Benzmüller, Christoph; Solopova, Veronika; Landgraf, Tim; u. a. (2023): Automated Multilingual Detection of Pro-Kremlin Propaganda in Newspapers and Telegram Posts, in: Datenbank-Spektrum : Zeitschrift für Datenbanktechnologie, Berlin: Springer, Jg. 25, Nr. 1, doi: 10.1007/s13222-023-00437-2.
Details
- Faculty/Chair
- Faculty/Professorship
- Author
- Solopova, VeronikaLandgraf, TimPopescu, Oana-Iuliana
- Title of the Journal
- Datenbank-Spektrum : Zeitschrift für Datenbanktechnologie
- ISSN
- 1610-19951618-2162
- Publisher Information
- Springer : Berlin
- Year of publication
- 2023
- Volume
- 25
- Issue
- 1
- Pages
- 5-14
- Language
- English
- DOI
- Abstract
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, French 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.
- GND Keywords
- PropagandaFalschmeldungAutomatische SprachanalyseMaschinelles LernenRussisch-Ukrainischer KriegContent <Internet>Moderation
- Keywords
- PropagandaFake newsNLPKremlinUkraineAutomated Content Moderation
- DDC Classification
- 004 Computer science
- RVK Classification
- ST 306
- Peer Reviewed
- yes
- International Distribution
- yes
- Open Access Journal
- no
- Type
- Article
- URI
- Activation date
- 2023-03-06