{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T15:52:28Z","timestamp":1792165948710,"version":"4.4.0"},"reference-count":70,"publisher":"Association for Computing Machinery (ACM)","issue":"CSCW2","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Hum.-Comput. Interact."],"published-print":{"date-parts":[[2024,11,7]]},"abstract":"<jats:p>The 2022 Russian invasion of Ukraine was accompanied by a large-scale, pro-Russian propaganda campaign on social media. However, the strategy behind the dissemination of propaganda has remained unclear, particularly how the online discourse was strategically shaped by the propagandists' community. Here, we analyze the strategy of the Twitter\/X community using an inverse reinforcement learning (IRL) approach. Specifically, IRL allows us to model online behavior as a Markov decision process, where the goal is to infer the underlying reward structure that guides propagandists when interacting with users with a supporting or opposing stance toward the invasion. Thereby, we aim to understand empirically whether and how between-user interactions are strategically used to promote the proliferation of Russian propaganda. For this, we leverage a large-scale dataset with 349,455 posts with pro-Russian propaganda from 132,131 users. We show that bots and humans follow a different strategy: bots respond predominantly to pro-invasion messages, suggesting that they seek to drive virality; in contrast, messages indicating opposition primarily elicit responses from humans, suggesting that they tend to engage in critical discussions. To the best of our knowledge, this is the first study analyzing the strategy behind propaganda from the 2022 Russian invasion of Ukraine through the lens of IRL.<\/jats:p>","DOI":"10.1145\/3686930","type":"journal-article","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T15:52:40Z","timestamp":1731081160000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Analyzing the Strategy of Propaganda using Inverse Reinforcement Learning: Evidence from the 2022 Russian Invasion of Ukraine"],"prefix":"10.1145","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0911-8745","authenticated-orcid":false,"given":"Dominique","family":"Geissler","sequence":"first","affiliation":[{"name":"LMU Munich &amp; Munich Center for Machine Learning (MCML), Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7856-8729","authenticated-orcid":false,"given":"Stefan","family":"Feuerriegel","sequence":"additional","affiliation":[{"name":"LMU Munich &amp; Munich Center for Machine Learning (MCML), Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,8]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Ng","author":"Abbeel Pieter","year":"2004","unstructured":"Pieter Abbeel and Andrew Y. Ng. 2004. Apprenticeship learning via inverse reinforcement learning. ICML (2004)."},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-022-00908-6"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-022-01375-x"},{"key":"e_1_2_2_4_1","volume-title":"Designing to support reflection on values & practices to address online disinformation. CSCW","author":"Arif Ahmer","year":"2018","unstructured":"Ahmer Arif. 2018. Designing to support reflection on values & practices to address online disinformation. CSCW (2018)."},{"key":"e_1_2_2_5_1","volume-title":"Analyzing the digital traces of political manipulation: The 2016 Russian interference Twitter campaign. ASONAM","author":"Badawy Adam","year":"2018","unstructured":"Adam Badawy, Emilio Ferrara, and Kristina Lerman. 2018. Analyzing the digital traces of political manipulation: The 2016 Russian interference Twitter campaign. ASONAM (2018)."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1906420116"},{"key":"e_1_2_2_7_1","volume-title":"Finding Qs: Profiling QAnon supporters on Parler. ICWSM","author":"B\u00e4r Dominik","year":"2023","unstructured":"Dominik B\u00e4r, Nicolas Pr\u00f6llochs, and Stefan Feuerriegel. 2023. Finding Qs: Profiling QAnon supporters on Parler. ICWSM (2023)."},{"key":"e_1_2_2_8_1","volume-title":"New threats to society from free-speech social media platforms. Commun. ACM","author":"B\u00e4r Dominik","year":"2023","unstructured":"Dominik B\u00e4r, Nicolas Pr\u00f6llochs, and Stefan Feuerriegel. 2023. New threats to society from free-speech social media platforms. Commun. ACM (2023)."},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_2_10_1","volume-title":"Measuring user influence in Twitter: The million follower fallacy. ICWSM","author":"Cha Meeyoung","year":"2010","unstructured":"Meeyoung Cha, Hamed Haddadi, Fabricio Benevenuto, and Krishna Gummadi. 2010. Measuring user influence in Twitter: The million follower fallacy. ICWSM (2010)."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_2_12_1","volume-title":"Support-vector networks. Machine Learning","author":"Cortes Corinna","year":"1995","unstructured":"Corinna Cortes and Vladimir Vapnik. 1995. Support-vector networks. Machine Learning (1995)."},{"key":"e_1_2_2_13_1","volume-title":"Rostislav Petrov, and Preslav Nakov.","author":"San Martino Giovanni Da","year":"2019","unstructured":"Giovanni Da San Martino, Seunghak Yu, Alberto Barr\u00f3n-Cede no, Rostislav Petrov, and Preslav Nakov. 2019. Fine-grained analysis of propaganda in news articles. EMNLP (2019)."},{"key":"e_1_2_2_14_1","volume-title":"The effects of feedback on human behavior in social media: An inverse reinforcement learning model. AAMAS","author":"Das Sanmay","year":"2014","unstructured":"Sanmay Das and Allen Lavoie. 2014. The effects of feedback on human behavior in social media: An inverse reinforcement learning model. AAMAS (2014)."},{"key":"e_1_2_2_15_1","first-page":"4662","article-title":"Trollfare: Russia's disinformation cmpaign during military conflict in Ukraine","volume":"15","author":"Doroshenko Larissa","year":"2021","unstructured":"Larissa Doroshenko and Josephine Lukito. 2021. Trollfare: Russia's disinformation cmpaign during military conflict in Ukraine. International Journal of Communication, Vol. 15 (2021), 4662--4689.","journal-title":"International Journal of Communication"},{"key":"e_1_2_2_16_1","volume-title":"First Monday","volume":"22","author":"Ferrara Emilio","year":"2017","unstructured":"Emilio Ferrara. 2017. Disinformation and social bot operations in the run up to the 2017 French presidential election. First Monday, Vol. 22, 8 (2017)."},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818717"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-020-00994-6"},{"key":"e_1_2_2_20_1","volume-title":"Weeks","author":"Kelly Garrett R.","year":"2013","unstructured":"R. Kelly Garrett and Brian E. Weeks. 2013. The promise and peril of real-time corrections to political misperceptions. CSCW (2013)."},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1140\/epjds\/s13688-023-00414-5"},{"key":"e_1_2_2_22_1","volume-title":"Messaging strategies of Ukraine and Russia on Telegram during the 2022 Russian invasion of Ukraine. First Monday","author":"Ghasiya Piyush","year":"2023","unstructured":"Piyush Ghasiya and Kazutoshi Sasahara. 2023. Messaging strategies of Ukraine and Russia on Telegram during the 2022 Russian invasion of Ukraine. First Monday (2023)."},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1057\/s41599-020-00659-9"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1093\/ia\/iiy148"},{"key":"e_1_2_2_25_1","volume-title":"Ukraine war: The stolen faces used to promote Vladimir Putin. BBC News","author":"Gragnani Juliana","year":"2022","unstructured":"Juliana Gragnani, Medhavi Arora, and Seraj Ali. 2022. Ukraine war: The stolen faces used to promote Vladimir Putin. BBC News (2022). https:\/\/www.bbc.com\/news\/blogs-trending-61351342"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40649-017-0042-6"},{"key":"e_1_2_2_27_1","volume-title":"Mauro Conti, and Preslav Nakov.","author":"Hristakieva Kristina","year":"2022","unstructured":"Kristina Hristakieva, Stefano Cresci, Giovanni Da San Martino, Mauro Conti, and Preslav Nakov. 2022. The spread of propaganda by coordinated communities on social media. WebSci (2022)."},{"key":"e_1_2_2_28_1","volume-title":"Still out there: Modeling and identifying Russian troll accounts on Twitter. WebSci","author":"Im Jane","year":"2020","unstructured":"Jane Im, Eshwar Chandrasekharan, Jackson Sargent, Paige Lighthammer, Taylor Denby, Ankit Bhargava, Libby Hemphill, David Jurgens, and Eric Gilbert. 2020. Still out there: Modeling and identifying Russian troll accounts on Twitter. WebSci (2020)."},{"key":"e_1_2_2_29_1","unstructured":"Garth Jowett and Victoria O'Donnell. 2012. Chapter 1: What is propaganda and how does it differ from persuasion? In Propaganda & persuasion. SAGE Los Angeles."},{"key":"e_1_2_2_30_1","unstructured":"Garth Jowett and Victoria O'Donnell. 2012. Chapter 2: Propaganda through the ages. In Propaganda & persuasion. SAGE Los Angeles."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"e_1_2_2_32_1","volume-title":"Knowledge Enhanced Masked Language Model for Stance Detection. NAACL","author":"Kawintiranon Kornraphop","year":"2021","unstructured":"Kornraphop Kawintiranon and Lisa Singh. 2021. Knowledge Enhanced Masked Language Model for Stance Detection. NAACL (2021)."},{"key":"e_1_2_2_33_1","volume-title":"LightGBM: A highly efficient gradient boosting decision tree. NeurIPS","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. LightGBM: A highly efficient gradient boosting decision tree. NeurIPS (2017)."},{"key":"e_1_2_2_34_1","volume-title":"Ullrich K. H. Ecker, Stephan Lewandowsky, and Ralph Hertwig.","author":"Kozyreva Anastasia","year":"2022","unstructured":"Anastasia Kozyreva, Philipp Lorenz-Spreen, Stefan Michael Herzog, Ullrich K. H. Ecker, Stephan Lewandowsky, and Ralph Hertwig. 2022. Toolbox of interventions against online misinformation and manipulation. PsyArXiv."},{"key":"e_1_2_2_35_1","volume-title":"Detecting troll behavior via inverse reinforcement learning: A case study of Russian trolls in the 2016 US election. ICWSM","author":"Luceri Luca","year":"2020","unstructured":"Luca Luceri, Silvia Giordano, and Emilio Ferrara. 2020. Detecting troll behavior via inverse reinforcement learning: A case study of Russian trolls in the 2016 US election. ICWSM (2020)."},{"key":"e_1_2_2_36_1","volume-title":"Which linguistic cues make people fall for fake news? A comparison of cognitive and affective processing. CSCW","author":"Lutz Bernhard","year":"2024","unstructured":"Bernhard Lutz, Marc Adam, Stefan Feuerriegel, Nicolas Pr\u00f6llochs, and Dirk Neumann. 2024. Which linguistic cues make people fall for fake news? A comparison of cognitive and affective processing. CSCW (2024)."},{"key":"e_1_2_2_37_1","volume-title":"HQP: A human-annotated dataset for detecting online propaganda. arXiv:2304.14931","author":"Maarouf Abdurahman","year":"2023","unstructured":"Abdurahman Maarouf, Dominik B\u00e4r, Dominique Geissler, and Stefan Feuerriegel. 2023. HQP: A human-annotated dataset for detecting online propaganda. arXiv:2304.14931 (2023)."},{"key":"e_1_2_2_38_1","volume-title":"The virality of hate speech on social media. CSCW","author":"Maarouf Abdurahman","year":"2024","unstructured":"Abdurahman Maarouf, Nicolas Pr\u00f6llochs, and Stefan Feuerriegel. 2024. The virality of hate speech on social media. CSCW (2024)."},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.54501\/jots.v1i2.30"},{"key":"e_1_2_2_40_1","volume-title":"Detection of sockpuppets in social media. CSCW","author":"Maity Suman Kalyan","year":"2017","unstructured":"Suman Kalyan Maity, Aishik Chakraborty, Pawan Goyal, and Animesh Mukherjee. 2017. Detection of sockpuppets in social media. CSCW (2017)."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.5210\/fm.v24i5.9638"},{"key":"e_1_2_2_42_1","volume-title":"Ng and Stuart Russel","author":"Andrew","year":"2000","unstructured":"Andrew Y. Ng and Stuart Russel. 2000. Algorithms for inverse reinforcement learning. ICML (2000)."},{"key":"e_1_2_2_43_1","volume-title":"Carley","author":"Xian Ng Lynnette Hui","year":"2022","unstructured":"Lynnette Hui Xian Ng and Kathleen M. Carley. 2022. Online Coordination: Methods and Comparative Case Studies of Coordinated Groups across Four Events in the United States. WebSci (2022), 12--21."},{"key":"e_1_2_2_44_1","volume-title":"BERTweet: A pre-trained language model for English tweets. EMNLP","author":"Nguyen Dat Quoc","year":"2020","unstructured":"Dat Quoc Nguyen, Thanh Vu, and Anh Tuan Nguyen. 2020. BERTweet: A pre-trained language model for English tweets. EMNLP (2020)."},{"key":"e_1_2_2_45_1","volume-title":"Coordinated behavior on social media in 2019 UK general election. ICWSM","author":"Nizzoli Leonardo","year":"2021","unstructured":"Leonardo Nizzoli, Serena Tardelli, Marco Avvenuti, Stefano Cresci, and Maurizio Tesconi. 2021. Coordinated behavior on social media in 2019 UK general election. ICWSM (2021)."},{"key":"e_1_2_2_46_1","volume-title":"Alessandro Flammini, and Filippo Menczer.","author":"Pacheco Diogo","year":"2021","unstructured":"Diogo Pacheco, Pik-Mai Hui, Christopher Torres-Lugo, Bao Tran Truong, Alessandro Flammini, and Filippo Menczer. 2021. Uncovering coordinated networks on social media: Methods and case studies. ICWSM (2021)."},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1037\/xge0000465"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03344-2"},{"key":"e_1_2_2_49_1","volume-title":"Propaganda and misinformation on Facebook and Twitter during the Russian invasion of Ukraine. WebSci","author":"Pierri Francesco","year":"2023","unstructured":"Francesco Pierri, Luca Luceri, Nikhil Jindal, and Emilio Ferrara. 2023. Propaganda and misinformation on Facebook and Twitter during the Russian invasion of Ukraine. WebSci (2023)."},{"key":"e_1_2_2_50_1","volume-title":"Mechanisms of true and false rumor sharing in social media: Wisdom-of-crowds or herd behavior? CSCW","author":"Pr\u00f6llochs Nicolas","year":"2023","unstructured":"Nicolas Pr\u00f6llochs and Stefan Feuerriegel. 2023. Mechanisms of true and false rumor sharing in social media: Wisdom-of-crowds or herd behavior? CSCW (2023)."},{"key":"e_1_2_2_51_1","volume-title":"Bayesian inverse reinforcement learning. IJCAI","author":"Ramachandran Deepak","year":"2007","unstructured":"Deepak Ramachandran and Eyal Amir. 2007. Bayesian inverse reinforcement learning. IJCAI (2007)."},{"key":"e_1_2_2_52_1","volume-title":"Svitlana Volkova, and Yejin Choi.","author":"Rashkin Hannah","year":"2017","unstructured":"Hannah Rashkin, Eunsol Choi, Jin Yea Jang, Svitlana Volkova, and Yejin Choi. 2017. Truth of varying shades: Analyzing language in fake news and political fact-checking. EMNLP (2017)."},{"key":"e_1_2_2_53_1","volume-title":"Detecting and tracking political abuse in social media. ICWSM","author":"Ratkiewicz Jacob","year":"2011","unstructured":"Jacob Ratkiewicz, Michael D. Conover, Mark Meiss, Bruno Goncalves, Alessandro Flammini, and Filippo Menczer. 2011. Detecting and tracking political abuse in social media. ICWSM (2011)."},{"key":"e_1_2_2_54_1","volume-title":"As war in Ukraine evolves, so do disinformation tactics. Politico","author":"Scott Mark","year":"2022","unstructured":"Mark Scott. 2022. As war in Ukraine evolves, so do disinformation tactics. Politico (2022). https:\/\/www.politico.eu\/article\/ukraine-russia-disinformation-propaganda\/"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-06930-7"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1177\/09564748221121468"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.2753\/MIS0742-1222290408"},{"key":"e_1_2_2_58_1","volume-title":"Barto","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement learning: An introduction. MIT press, Cambridge, Massachusetts."},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1080\/03071847.2015.1079047"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1177\/105971239700500302"},{"key":"e_1_2_2_61_1","volume-title":"Russia's use of social media with additional views.","author":"Senate US","year":"2019","unstructured":"US Senate. 2019. Report of the select committee on intelligence United States Senate on Russian active measures campaigns and interference in the 2016 U.S. election volume 2: Russia's use of social media with additional views. (2019)."},{"key":"e_1_2_2_62_1","volume-title":"Propaganda detection in Russian Telegram posts in the scope of the Russian invasion of Ukraine. RANLP","author":"Vanetik Natalia","year":"2023","unstructured":"Natalia Vanetik, Marina Litvak, Egor Reviakin, and Margarita Tiamanova. 2023. Propaganda detection in Russian Telegram posts in the scope of the Russian invasion of Ukraine. RANLP (2023)."},{"key":"e_1_2_2_63_1","volume-title":"On the detection of disinformation campaign activity with network analysis. CCSW","author":"Vargas Luis","year":"2020","unstructured":"Luis Vargas, Patrick Emami, and Patrick Traynor. 2020. On the detection of disinformation campaign activity with network analysis. CCSW (2020)."},{"key":"e_1_2_2_64_1","volume-title":"Online human-bot interactions: Detection, estimation, and characterization. ICWSM","author":"Varol Onur","year":"2017","unstructured":"Onur Varol, Emilio Ferrara, Clayton A. Davis, Filippo Menczer, and Alessandro Flammini. 2017. Online human-bot interactions: Detection, estimation, and characterization. ICWSM (2017)."},{"key":"e_1_2_2_65_1","volume-title":"Science","volume":"359","author":"Vosoughi Soroush","year":"2018","unstructured":"Soroush Vosoughi, Deb Roy, and Sinan Aral. 2018. The spread of true and false news online. Science, Vol. 359, 6380 (2018), 1146--1151."},{"key":"e_1_2_2_66_1","volume-title":"Learning from delayed rewards. Ph.D. diss","author":"Christopher J. C. H.","unstructured":"Watkins, Christopher J. C. H. 1989. Learning from delayed rewards. Ph.D. diss. King's College, Camebridge, UK."},{"key":"e_1_2_2_67_1","volume-title":"Bots in the Twittersphere","author":"Wojcik Stefan","year":"2018","unstructured":"Stefan Wojcik, Solomon Messing, Aaron Smith, Lee Rainie, and Paul Hitlin. 2018. Bots in the Twittersphere. Pew Research Center (2018). https:\/\/www.pewresearch.org\/internet\/2018\/04\/09\/bots-in-the-twittersphere\/"},{"key":"e_1_2_2_68_1","volume-title":"Maximum entropy deep inverse reinforcement learning. arXiv:1507.04888","author":"Wulfmeier Markus","year":"2015","unstructured":"Markus Wulfmeier, Peter Ondruska, and Ingmar Posner. 2015. Maximum entropy deep inverse reinforcement learning. arXiv:1507.04888 (2015)."},{"key":"e_1_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-022-01399-3"},{"key":"e_1_2_2_70_1","volume-title":"Dey","author":"Ziebart Brian D.","year":"2008","unstructured":"Brian D. Ziebart, Andrew Maas, J. Andrew Bagnell, and Anind K. Dey. 2008. Maximum entropy inverse reinforcement learning. AAAI (2008)."}],"container-title":["Proceedings of the ACM on Human-Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3686930","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3686930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T09:19:47Z","timestamp":1755767987000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3686930"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":70,"journal-issue":{"issue":"CSCW2","published-print":{"date-parts":[[2024,11,7]]}},"alternative-id":["10.1145\/3686930"],"URL":"https:\/\/doi.org\/10.1145\/3686930","relation":{},"ISSN":["2573-0142"],"issn-type":[{"value":"2573-0142","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,7]]},"assertion":[{"value":"2024-11-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}