Abstract
There are organized groups that disseminate similar messages in online forums and social media; they respond to real-time events or as persistent policy, and operate with state-level or organizational funding. Identifying these groups is of vital importance for preventing distribution of sponsored propaganda and misinformation. This paper presents an unsupervised approach using behavioral and text analysis of users and messages to identify groups of users who abuse the Twitter micro-blogging service to disseminate propaganda and misinformation. Groups of users who frequently post strikingly similar content at different times are identified through repeated clustering and frequent itemset mining, with the lack of credibility of their content validated through human assessment. This paper introduces a case study into automatic identification of propagandists and misinformers in social media.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
VK is a social network popular in Russia, see https://vk.com.
- 2.
Propaganda is defined as: “posts that contain information, especially of a biased or misleading nature, that is used to promote or publicize a particular political cause or point of view” (Oxford English Dictionary, 3rd Online Edition).
- 3.
A tweet was considered as a document, and collection of all tweets as a corpus.
- 4.
By “user” we mean account and not individual, based on assumption (4).
- 5.
Edge weights are normalized to be in range of [0, 1].
- 6.
Topic modeling was performed using KNIME’s LDA implementation.
- 7.
References
Agrawal, R., Mannila, H., Srikant, R., Toivonen, H., Verkamo, A.I., et al.: Fast discovery of association rules. Adv. Knowl. Discov. Data Min. 12(1), 307–328 (1996)
Akoglu, L., Chandy, R., Faloutsos, C.: Opinion fraud detection in online reviews by network effects. In: ICWSM 2013, pp. 2–11 (2013)
Allcott, H., Gentzkow, M.: Social media and fake news in the 2016 election. J. Econ. Perspect. 31(2), 211–36 (2017)
Berthold, M.R., et al.: KNIME: the Konstanz information miner. In: Preisach, C., Burkhardt, H., Schmidt-Thieme, L., Decker, R. (eds.) Data Analysis, Machine Learning and Applications. Studies in Classification, Data Analysis, and Knowledge Organization, pp. 319–326. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-78246-9_38
Castillo, C., Mendoza, M., Poblete, B.: Information credibility on Twitter. In: Proceedings of the 20th International Conference on World Wide Web, WWW 2011, pp. 675–684. ACM, New York (2011). https://doi.org/10.1145/1963405.1963500
Chen, Y., Conroy, N.J., Rubin, V.L.: Misleading online content: recognizing clickbait as false news. In: Proceedings of the 2015 ACM on Workshop on Multimodal Deception Detection, pp. 15–19. ACM (2015)
Conroy, N.J., Rubin, V.L., Chen, Y.: Automatic deception detection: methods for finding fake news. Proc. Assoc. Inf. Sci. Technol. 52(1), 1–4 (2015)
Hamidian, S., Diab, M.T.: Rumor identification and belief investigation on Twitter. In: WASSA@ NAACL-HLT, pp. 3–8 (2016)
Kleinberg, J.M., Kumar, R., Raghavan, P., Rajagopalan, S., Tomkins, A.S.: The web as a graph: measurements, models, and methods. In: Asano, T., Imai, H., Lee, D.T., Nakano, S., Tokuyama, T. (eds.) COCOON 1999. LNCS, vol. 1627, pp. 1–17. Springer, Heidelberg (1999). https://doi.org/10.1007/3-540-48686-0_1
Li, Z.C., He, P.L., Lei, M.: A high efficient AprioriTid algorithm for mining association rule. In: 2005 International Conference on Machine Learning and Cybernetics, vol. 3, pp. 1812–1815. IEEE, August 2005. https://doi.org/10.1109/ICMLC.2005.1527239
Lumezanu, C., Feamster, N., Klein, H.: #bias: measuring the tweeting behavior of propagandists. In: Sixth International AAAI Conference on Weblogs and Social Media (2012). http://www.aaai.org/ocs/index.php/ICWSM/ICWSM12/paper/view/4588
Meduza: Authors of paid comments in support of Moscow authorities forgot to edit assignment (2017). https://meduza.io/shapito/2017/02/03/avtory-platnyh-kommentariev-v-podderzhku-moskovskih-vlastey-zabyli-otredaktirovat-zadanie
Mehta, B., Hofmann, T., Fankhauser, P.: Lies and propaganda: detecting spam users in collaborative filtering. In: Proceedings of the 12th International Conference on Intelligent User Interfaces, pp. 14–21. ACM (2007). https://doi.org/10.1145/1216295.1216307
Mendoza, M., Poblete, B., Castillo, C.: Twitter under crisis: can we trust what we RT? In: Proceedings of the First Workshop on Social Media Analytics, SOMA 2010, pp. 71–79. ACM, New York (2010). https://doi.org/10.1145/1964858.1964869
Metaxas, P.: Using propagation of distrust to find untrustworthy web neighborhoods. In: 2009 Fourth International Conference on Internet and Web Applications and Services, ICIW 2009, pp. 516–521. IEEE (2009). https://doi.org/10.1109/ICIW.2009.83
Paul, C., Matthews, M.: The Russian “Firehose of Falsehood” Propaganda Model. RAND Corporation, Santa Monica (2016)
Qazvinian, V., Rosengren, E., Radev, D.R., Mei, Q.: Rumor has it: identifying misinformation in microblogs. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP 2011, pp. 1589–1599. Association for Computational Linguistics, Stroudsburg (2011). https://www.aclweb.org/anthology/D11-1147
Salton, G., Wong, A., Yang, C.S.: A vector space model for automatic indexing. Commun. ACM 18(11), 613–620 (1975)
The Alliance for Securing Democracy: Hamilton 68 (2017). https://dashboard.securingdemocracy.org
Volkova, S., Shaffer, K., Jang, J.Y., Hodas, N.: Separating facts from fiction: linguistic models to classify suspicious and trusted news posts on Twitter. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Short Papers, vol. 2, pp. 647–653 (2017)
Zubiaga, A., Liakata, M., Procter, R., Bontcheva, K., Tolmie, P.: Towards detecting rumours in social media. In: AAAI Workshop: AI for Cities (2015)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Orlov, M., Litvak, M. (2019). Using Behavior and Text Analysis to Detect Propagandists and Misinformers on Twitter. In: Lossio-Ventura, J., Muñante, D., Alatrista-Salas, H. (eds) Information Management and Big Data. SIMBig 2018. Communications in Computer and Information Science, vol 898. Springer, Cham. https://doi.org/10.1007/978-3-030-11680-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-11680-4_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-11679-8
Online ISBN: 978-3-030-11680-4
eBook Packages: Computer ScienceComputer Science (R0)