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 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.
Abstract (translated)
俄罗斯联邦和乌克兰的全面冲突导致了前所未有的新闻文章和社交媒体数据,反映了反对意识形态和叙事的对立。这些极化的运动导致了互相指责虚假信息和假新闻,为全球读者创造了一种混乱和不信任的氛围。本研究使用乌克兰语、俄语、罗马尼亚语和英语的新闻文章和 Telegram 新闻频道,探讨了在战争头一个月中,媒体如何影响和反映公众观点。我们提出了并比较了基于Transformer和语言学特征的两种多语言自动化反克里姆林宫宣传识别方法。我们分析了两种方法的优势和劣势,以及它们对新类型和语言 adaptability 的适应性,以及用于内容 moderation 的伦理考虑。通过这项工作,我们旨在为当前冲突量身定制的 moderation 工具的发展打下基础。
URL
https://arxiv.org/abs/2301.10604