Topic modeling for analysing the Russian propaganda in the conflict with Ukraine Maria Gabriella Grassia University of Naples Federico II, Italy Marina Marino University of Naples Federico II, Italy Rocco Mazza University of Naples Federico II, Italy Michelangelo Misuraca University of Calabria, Italy Agostino Stavolo University of Naples Federico II, Italy This is a section of ASA 2022 Data-Driven Decision Making(DOI: 10.36253/979-12-215-0106-3) by Enrico di Bella, Luigi Fabbris, Corrado Lagazio Firenze University Press Firenze 2023 https://doi.org/10.36253/979-12-215-0106-3.43

Available for academic research purposes

Open Access

Copyright Author(s)

Content licence CC BY 4.0

Metadata licence CC0 1.0

This is original content, published for academic research purposes

 Digital edition XML powered by Booksflow

The conflict between Ukraine and Russia is changing Europe, which is facing a crisis destined to reshape the internal and external relations of the continent, shifting international balances. In this contribution, we show preliminary results on the monitoring of Russian propaganda. In fact, we analysed the content of online newspapers (Strategic Culture Foundation, Global research, News Front, South Front, Katehon, Geopolitics) used as propaganda tools of the Russian government. The newspapers create and amplify the narrative of the conflict, transmitting information filtered by the Kremlin to advance Putin's propaganda about the war. The objective of the work, therefore, is to understand what were the main themes that the Russian media used to motivate the conflict in Ukraine. Specifically, the proposed analysis runs from March 2021, when the Russian military began moving weapons and equipment into Crimea, to the end of March 2022, the day of the first negotiations in Istanbul. In this regard, we used topic modeling techniques to analyse textual content that uncovers the latent thematic structure in document collections to identify emerging topics.

 topic modeling russian propaganda non-negative matrix factorization

It is available online at https://doi.org/10.36253/979-12-215-0106-3.43

References Abd Kadir, S., Abu Hasan, A. S. (2014). A content analysis of propaganda in Harakah newspaper. Journal of Media and Information Warfare (JMIW) Casalino, G., Del Buono, N., Mencar, C. (2016). Nonnegative matrix factorizations for intelligent data analysis. Non-negative Matrix Factorization Techniques (pp. 49-74). Springer, Berlin, Heidelberg. Jia, Y., Liu, H., Hou, J., Kwong, S., Zhang, Q. (2021). Self-supervised symmetric nonnegative matrix factorization. IEEE Transactions on Circuits and Systems for Video Technology. Kim, J., Park H., (2008) Sparse nonnegative matrix factorization for clustering, Georgia Inst. of Technology, Tech. Rep. Kuang, D., Choo, J., Park, H. (2015). Nonnegative matrix factorization for interactive topic modeling and document clustering, in Partitional Clustering Algorithms (pp. 215-243). Springer, Cham. Moutier, F., Vandaele, A., Gillis, N. (2021). Off-diagonal symmetric nonnegative matrix factorization. Numerical Algorithms, 88(2), 939-963. Ng, A., Jordan, M., Weiss, Y. (2001). On spectral clustering: Analysis and an algorithm. Advances in neural information processing systems, 14. Pauca, V. P., Shahnaz, F., Berry, M. W., Plemmons, R. J. (2004). Text mining using non-negative matrix factorizations, in Proceedings of the 2004 SIAM International Conference on Data Mining (pp. 452-456). Society for Industrial and Applied Mathematics. Pratkanis, A., Aronson, E. (1991). What is news? In Age of Propaganda: The Everyday Use and Abuse of Persuasion, (pp. 32 – 39). New York: W. H. Freeman. U.S. Department of State, GEC Special Report (2020). Pillars of Russia’s Disinformation and Propaganda Ecosystem, https://www.state.gov/wp-content/uploads/2020/08/Pillars-of-Russia%E2%80%99s-Disinformation-and-Propaganda-Ecosystem_08-04-20.pdf Yan, X., Guo, J., Liu, S., Cheng, X., Wang, Y. (2013). Learning topics in short texts by non-negative matrix factorization on term correlation matrix, in Proceedings of the 2013 SIAM International Conference on Data Mining (pp. 749-757), Society for Indus