Detecting Propaganda Techniques in Memes

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pages 6603–6617 August 1–6, 2021. ©2021 Association for Computational Linguistics 6603 Detecting Propaganda Techniques in Memes Dimitar Dimitrov,1 Bishr Bin Ali,2 Shaden Shaar,3 Firoj Alam,3 Fabrizio Silvestri,4 Hamed Firooz,5 Preslav Nakov, 3 and Giovanni Da San Martino6 1 Sofia University “St. Kliment Ohridski”, Bulgaria, 2 King’s College London, UK, 3 Qatar Computing Research Institute, HBKU, Qatar 4 Sapienza University of Rome, Italy, 5 Facebook AI, USA, 6 University of Padova, Italy mitko.bg.ss@gmail.com, bishrkc@gmail.com {sshaar, fialam, pnakov}@hbku.edu.qa, mhfirooz@fb.com fsilvestri@diag.uniroma1.it, dasan@math.unipd.it Abstract Propaganda can be defined as a form of com- munication that aims to influence the opinions or the actions of people towards a specific goal; this is achieved by means of well-defined rhetorical and psychological devices. Propa- ganda, in the form we know it today, can be dated back to the beginning of the 17th cen- tury. However, it is with the advent of the In- ternet and the social media that it has started to spread on a much larger scale than before, thus becoming major societal and political is- sue. Nowadays, a large fraction of propaganda in social media is multimodal, mixing textual with visual content. With this in mind, here we propose a new multi-label multimodal task: de- tecting the type of propaganda techniques used in memes. We further create and release a new corpus of 950 memes, carefully annotated with 22 propaganda techniques, which can appear in the text, in the image, or in both. Our anal- ysis of the corpus shows that understanding both modalities together is essential for detect- ing these techniques. This is further confirmed in our experiments with several state-of-the-art multimodal models. 1 Introduction Social media have become one of the main com- munication channels for information dissemination and consumption, and nowadays many people rely on them as their primary source of news (Perrin, 2015). Despite the many benefits that social media offer, sporadically they are also used as a tool, by bots or human operators, to manipulate and to mis- lead unsuspecting users. Propaganda is one such communication tool to influence the opinions and the actions of other people in order to achieve a predetermined goal (IPA, 1938). WARNING: This paper contains meme examples and words that are offensive in nature. Propaganda is not new. It can be traced back to the beginning of the 17th century, as reported in (Margolin, 1979; Casey, 1994; Martino et al., 2020), where the manipulation was present at pub- lic events such as theaters, festivals, and during games. In the current information ecosystem, it has evolved to computational propaganda (Wool- ley and Howard, 2018; Martino et al., 2020), where information is distributed through technological means to social media platforms, which in turn make it possible to reach well-targeted communi- ties at high velocity. We believe that being aware and able to detect propaganda campaigns would contribute to a healthier online environment. Propaganda appears …

Content truncated to 500 words