Automated Multilingual Detection of Pro-Kremlin Propaganda in Newspapers and Telegram Posts

Datenbank-Spektrum : Zeitschrift fur Datenbanktechnologie : Organ der Fachgruppe Datenbanken der Gesellschaft fur Informatik e.V Pub Date : 2023-03-01 DOI:10.1007/s13222-023-00437-2

Veronika Solopova, Oana-Iuliana Popescu, Christoph Benzmüller, Tim Landgraf

{"title":"Automated Multilingual Detection of Pro-Kremlin Propaganda in Newspapers and Telegram Posts","authors":"Veronika Solopova, Oana-Iuliana Popescu, Christoph Benzmüller, Tim Landgraf","doi":"10.1007/s13222-023-00437-2","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":72771,"journal":{"name":"Datenbank-Spektrum : Zeitschrift fur Datenbanktechnologie : Organ der Fachgruppe Datenbanken der Gesellschaft fur Informatik e.V","volume":"760 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Datenbank-Spektrum : Zeitschrift fur Datenbanktechnologie : Organ der Fachgruppe Datenbanken der Gesellschaft fur Informatik e.V","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s13222-023-00437-2","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

Abstract

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.

查看原文本刊更多论文

报纸和电报中亲克里姆林宫宣传的多语种自动检测

俄罗斯联邦和乌克兰之间的全面冲突产生了前所未有的反映对立意识形态和叙事的新闻文章和社交媒体数据。这些两极分化的运动导致了对虚假信息和假新闻的相互指责，给全世界的读者造成了一种困惑和不信任的氛围。本研究分析了在战争的第一个月，媒体是如何通过乌克兰语、俄语、罗马尼亚语、法语和英语的新闻文章和电报新闻频道影响和反映公众舆论的。我们提出并比较了基于变形金刚和语言特征的两种多语言亲克里姆林宫宣传自动识别方法。我们分析了这两种方法的优缺点，它们对新体裁和语言的适应性，以及它们用于内容审核的伦理考虑。通过这项工作，我们的目标是为进一步开发适合当前冲突的节制工具奠定基础。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Datenbank-Spektrum : Zeitschrift fur Datenbanktechnologie : Organ der Fachgruppe Datenbanken der Gesellschaft fur Informatik e.V

自引率

0.00%

发文量