Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Russo-Ukrainian War: Prediction and explanation of Twitter suspension (2306.03502v2)

Published 6 Jun 2023 in cs.SI, cs.AI, and cs.LG

Abstract: On 24 February 2022, Russia invaded Ukraine, starting what is now known as the Russo-Ukrainian War, initiating an online discourse on social media. Twitter as one of the most popular SNs, with an open and democratic character, enables a transparent discussion among its large user base. Unfortunately, this often leads to Twitter's policy violations, propaganda, abusive actions, civil integrity violation, and consequently to user accounts' suspension and deletion. This study focuses on the Twitter suspension mechanism and the analysis of shared content and features of the user accounts that may lead to this. Toward this goal, we have obtained a dataset containing 107.7M tweets, originating from 9.8 million users, using Twitter API. We extract the categories of shared content of the suspended accounts and explain their characteristics, through the extraction of text embeddings in junction with cosine similarity clustering. Our results reveal scam campaigns taking advantage of trending topics regarding the Russia-Ukrainian conflict for Bitcoin and Ethereum fraud, spam, and advertisement campaigns. Additionally, we apply a machine learning methodology including a SHapley Additive explainability model to understand and explain how user accounts get suspended.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. S. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” arXiv preprint arXiv:1705.07874, 2017.
  2. T. Verge, “Twitter accounts sharing video from ukraine are being suspended when they’re needed most.” https://shorturl.at/jALOU, 2022, accessed: 2023-07-19.
  3. F. A. Chowdhury, L. Allen, M. Yousuf, and A. Mueen, “On twitter purge: A retrospective analysis of suspended users,” in Companion Proceedings of the Web Conference 2020, 2020, pp. 371–378.
  4. S. Volkova and E. Bell, “Identifying effective signals to predict deleted and suspended accounts on twitter across languages,” in Proceedings of the International AAAI Conference on Web and Social Media, vol. 11, no. 1, 2017, pp. 290–298.
  5. F. A. Chowdhury, D. Saha, M. R. Hasan, K. Saha, and A. Mueen, “Examining factors associated with twitter account suspension following the 2020 us presidential election,” in Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2021, pp. 607–612.
  6. A. M. Founta, C. Djouvas, D. Chatzakou, I. Leontiadis, J. Blackburn, G. Stringhini, A. Vakali, M. Sirivianos, and N. Kourtellis, “Large scale crowdsourcing and characterization of twitter abusive behavior,” in Twelfth International AAAI Conference on Web and Social Media, 2018.
  7. T. Davidson, D. Warmsley, M. Macy, and I. Weber, “Automated hate speech detection and the problem of offensive language,” in Proceedings of the International AAAI Conference on Web and Social Media, vol. 11, no. 1, 2017, pp. 512–515.
  8. P. Nakov, V. Nayak, K. Dent, A. Bhatawdekar, S. M. Sarwar, M. Hardalov, Y. Dinkov, D. Zlatkova, G. Bouchard, and I. Augenstein, “Detecting abusive language on online platforms: A critical analysis,” arXiv preprint arXiv:2103.00153, 2021.
  9. E. Ferrara, H. Chang, E. Chen, G. Muric, and J. Patel, “Characterizing social media manipulation in the 2020 us presidential election,” First Monday, 2020.
  10. Z. Chu, S. Gianvecchio, H. Wang, and S. Jajodia, “Detecting automation of twitter accounts: Are you a human, bot, or cyborg?” IEEE Transactions on dependable and secure computing, vol. 9, no. 6, pp. 811–824, 2012.
  11. X. Zhang, S. Zhu, and W. Liang, “Detecting spam and promoting campaigns in the twitter social network,” in 2012 IEEE 12th international conference on data mining.   IEEE, 2012, pp. 1194–1199.
  12. K. Thomas, C. Grier, D. Song, and V. Paxson, “Suspended accounts in retrospect: an analysis of twitter spam,” in Proceedings of the 2011 ACM SIGCOMM conference on Internet measurement conference, 2011, pp. 243–258.
  13. D. Antonakaki, I. Polakis, E. Athanasopoulos, S. Ioannidis, and P. Fragopoulou, “Exploiting abused trending topics to identify spam campaigns in twitter,” Social Network Analysis and Mining, vol. 6, no. 1, pp. 1–11, 2016.
  14. A. Shevtsov, C. Tzagkarakis, D. Antonakaki, and S. Ioannidis, “Identification of twitter bots based on an explainable machine learning framework: The us 2020 elections case study,” Proceedings of the International AAAI Conference on Web and Social Media, vol. 16, no. 1, pp. 956–967, May 2022. [Online]. Available: https://ojs.aaai.org/index.php/ICWSM/article/view/19349
  15. D. Antonakaki, P. Fragopoulou, and S. Ioannidis, “A survey of twitter research: Data model, graph structure, sentiment analysis and attacks,” Expert Systems with Applications, vol. 164, p. 114006, 2021.
  16. K. Thomas, F. Li, C. Grier, and V. Paxson, “Consequences of connectivity: Characterizing account hijacking on twitter,” in Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security, 2014, pp. 489–500.
  17. S. Zannettou, T. Caulfield, E. De Cristofaro, M. Sirivianos, G. Stringhini, and J. Blackburn, “Disinformation warfare: Understanding state-sponsored trolls on twitter and their influence on the web,” in Companion proceedings of the 2019 world wide web conference, 2019, pp. 218–226.
  18. J. Im, E. Chandrasekharan, J. Sargent, P. Lighthammer, T. Denby, A. Bhargava, L. Hemphill, D. Jurgens, and E. Gilbert, “Still out there: Modeling and identifying russian troll accounts on twitter,” in 12th ACM Conference on Web Science, 2020, pp. 1–10.
  19. K. Fiok, W. Karwowski, E. Gutierrez, and M. Wilamowski, “Analysis of sentiment in tweets addressed to a single domain-specific twitter account: Comparison of model performance and explainability of predictions,” Expert Systems with Applications, vol. 186, p. 115771, 2021.
  20. F. Morstatter, L. Wu, T. H. Nazer, K. M. Carley, and H. Liu, “A new approach to bot detection: striking the balance between precision and recall,” in 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).   IEEE, 2016, pp. 533–540.
  21. M. Kouvela, I. Dimitriadis, and A. Vakali, “Bot-detective: An explainable twitter bot detection service with crowdsourcing functionalities,” in Proceedings of the 12th International Conference on Management of Digital EcoSystems, 2020, pp. 55–63.
  22. J. C. Reis, A. Correia, F. Murai, A. Veloso, and F. Benevenuto, “Explainable machine learning for fake news detection,” in Proceedings of the 10th ACM conference on web science, 2019, pp. 17–26.
  23. E. Puraivan, E. Godoy, F. Riquelme, and R. Salas, “Fake news detection on twitter using a data mining framework based on explainable machine learning techniques,” 2021.
  24. A. Kapoor, R. R. Jain, A. Prabhu, T. Karandikar, and P. Kumaraguru, ““i’ll be back”: Examining restored accounts on twitter,” in IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, 2021, pp. 71–78.
  25. M. M. Yildirim, J. Nagler, R. Bonneau, and J. A. Tucker, “Short of suspension: How suspension warnings can reduce hate speech on twitter,” Perspectives on Politics, pp. 1–13, 2021.
  26. D. Chatzakou, N. Kourtellis, J. Blackburn, E. De Cristofaro, G. Stringhini, and A. Vakali, “Mean birds: Detecting aggression and bullying on twitter,” in Proceedings of the 2017 ACM on web science conference, 2017, pp. 13–22.
  27. W. Wei, K. Joseph, H. Liu, and K. M. Carley, “Exploring characteristics of suspended users and network stability on twitter,” Social network analysis and mining, vol. 6, no. 1, pp. 1–18, 2016.
  28. S. Ghosh, B. Viswanath, F. Kooti, N. K. Sharma, G. Korlam, F. Benevenuto, N. Ganguly, and K. P. Gummadi, “Understanding and combating link farming in the twitter social network,” in Proceedings of the 21st international conference on World Wide Web, 2012, pp. 61–70.
  29. M. C. Benigni, K. Joseph, and K. M. Carley, “Online extremism and the communities that sustain it: Detecting the isis supporting community on twitter,” PloS one, vol. 12, no. 12, p. e0181405, 2017.
  30. F. Feng, Y. Yang, D. Cer, N. Arivazhagan, and W. Wang, “Language-agnostic bert sentence embedding,” arXiv preprint arXiv:2007.01852, 2020.
  31. S. W. Min, K. Wu, S. Huang, M. Hidayetoğlu, J. Xiong, E. Ebrahimi, D. Chen, and W.-m. Hwu, “Pytorch-direct: Enabling gpu centric data access for very large graph neural network training with irregular accesses,” arXiv preprint arXiv:2101.07956, 2021.
  32. A. Lerer, L. Wu, J. Shen, T. Lacroix, L. Wehrstedt, A. Bose, and A. Peysakhovich, “Pytorch-biggraph: A large scale graph embedding system,” Proceedings of Machine Learning and Systems, vol. 1, pp. 120–131, 2019.
  33. A. Shevtsov, M. Oikonomidou, D. Antonakaki, P. Pratikakis, A. Kanterakis, P. Fragopoulou, and S. Ioannidis, “Discovery and classification of twitter bots,” SN Computer Science, vol. 3, no. 3, pp. 1–29, 2022.
  34. DomainToolsResearch, “Crypto winter: Fraudsters impersonate ukraine’s government to steal nfts and cryptocurrency,” https://www.domaintools.com/resources/blog/fraudsters-impersonate-ukraines-government-stealing-nfts-crypto/, 2022.
  35. L. Hanu and Unitary team, “Detoxify,” Github. https://github.com/unitaryai/detoxify, 2020.
  36. E. Mosca, F. Szigeti, S. Tragianni, D. Gallagher, and G. Groh, “Shap-based explanation methods: a review for nlp interpretability,” in Proceedings of the 29th International Conference on Computational Linguistics, 2022, pp. 4593–4603.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Alexander Shevtsov (5 papers)
  2. Despoina Antonakaki (8 papers)
  3. Ioannis Lamprou (8 papers)
  4. Ioannis Kontogiorgakis (2 papers)
  5. Polyvios Pratikakis (15 papers)
  6. Sotiris Ioannidis (41 papers)
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now