Skip to main content
SpringerLink
Log in

A longitudinal dataset and analysis of Twitter ISIS users and propaganda

  • Original Article
  • Published:
Social Network Analysis and Mining Aims and scope Submit manuscript

Abstract

Although ISIS was driven out of its last territory in Syria and its physical caliphate collapsed in 2019, recent terrorist attacks and incidents in various areas, such as Central Africa, and recently designated terrorists by the Department of State signify the presence and growth of ISIS affiliates. Yet, once under scrutiny, their whereabouts have been less known and studied since then. In this paper, we aim to reopen this line of investigation to further our understanding of the recent ISIS online presence. We collect and analyze a longitudinal dataset of tweets from potential ISIS affiliates and an existing dataset of ISIS Twitter activities around 2015—when Twitter cracked down on many ISIS accounts. We build a user classifier to identify ISIS supporters on Twitter. We further investigate different types of content and topics used by known ISIS accounts and compare these attributes among ISIS and its potential affiliates. We also identify messages that gained abnormal attention and support and presumably were used to spread propaganda and influence and manipulate the online community. Finally, we build and evaluate an image classifier using the residual network pretrained image classification models to categorize the photos attached to the candidate propaganda tweets of ISIS and identify the major themes in those media files.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Algorithm 1
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Notes

  1. Also known as the Islamic State in Iraq and al-Sham, the Islamic State of Iraq and the Levant (ISIL), the Islamic State (IS), and in Arabic, Daesh (an acronym formed from the initial letters of the group’s previous name in Arabic—“al-Dawla al-Islamiya fil Iraq wa al-Sham”—which means to tread underfoot, trample down, or crush something, and sounds unpleasant to their supporters) is a militant Sunni Islamist extremist group that follows a Salafi jihadist doctrine.

  2. https://t.me/ISISwatch

  3. https://www.state.gov/designations-of-isis-mozambique-jnim-and-al-shabaab-leaders

  4. https://warontherocks.com/2021/04/foreign-fighters-and-the-trajectory-of-violence-in-northern-mozambique

  5. https://en.wikipedia.org/wiki/Anonymous_(hacker_group)

  6. As of 2021, four Twitter users with similar usernames of @CtrlSec (https://twitter.com/CtrlSec), @CtrlSec0, @CtrlSec1, and @CtrlSec2 are directly associated to this campaign.

  7. https://developer.twitter.com/en/docs/twitter-api/tweets/timelines/introduction

  8. https://blog.twitter.com/en_us/topics/product/2022/introducing-mixed-media-videos-images-gifs-together-one-tweet

  9. We used https://www.wordclouds.com to generate the word clouds.

  10. https://www.masrawy.com/News/News_PublicAffairs/details/2014/7/25/299108

  11. https://en.wikipedia.org/wiki/Qasem_Soleimani

  12. https://en.wikipedia.org/wiki/Nimr_al-Nimr

  13. https://en.wikipedia.org/wiki/Abdulaziz_al-Fagham

  14. https://en.wikipedia.org/wiki/Mohammed_bin_Salman

  15. https://fasttext.cc/docs/en/crawl-vectors.html

  16. This uniqueness is solely based on the tweet IDs, the author of the tweets, and the media keys. We did not remove photos that are visual duplicates.

  17. https://pypi.org/project/ArabicOcr

  18. https://t.me/ISISwatch

  19. IS-K or ISIS-K stands for the Islamic State - Khorasan Province.

  20. https://www.kaggle.com/datasets/fifthtribe/how-isis-uses-twitter

  21. https://en.wikipedia.org/wiki/Al-Naba

  22. https://pastebin.com

  23. https://8kun.top

  24. Twitter Moderation Research Consortium: https://transparency.twitter.com/en/reports/moderation-research.html

References

  • Ahmad S, Asghar MZ, Alotaibi FM, Awan I (2019) Detection and classification of social media-based extremist affiliations using sentiment analysis techniques. HCIS 9:1–23

    Google Scholar 

  • Aïmeur E, Amri S, Brassard G (2023) Fake news, disinformation and misinformation in social media: a review. Soc Netw Anal Min 13(1):30

    Article  Google Scholar 

  • Alfifi M, Kaghazgaran P, Caverlee J, Morstatter F (2019) A large-scale study of ISIS social media strategy: community size, collective influence, and behavioral impact. Proc Int AAAI Conf Web Soc Med 13(01):58–67

    Article  Google Scholar 

  • Alfifi M, Kaghazgaran P, Caverlee J, Morstatter F (2018) Measuring the impact of isis social media strategy. MIS2. Marina Del Ray, California

  • Amarasingam A (2020) Telegram Deplatforming ISIS Has Given Them Something to Fight for. https://www.voxpol.eu/telegram-deplatforming-isis-has-given-them-something-to-fight-for. [Online; accessed 9-January-2022]

  • Badawy A, Ferrara E (2017) The rise of jihadist propaganda on social networks. SSRN Electron J. https://doi.org/10.2139/ssrn.2982256

    Article  Google Scholar 

  • Barrón-Cedeno A, Jaradat I, Da San Martino G, Nakov P (2019) Proppy: organizing the news based on their propagandistic content. Inform Process Manag 56(5):1849–1864

    Article  Google Scholar 

  • Benigni M, Carley KM (2016) From tweets to intelligence: Understanding the islamic jihad supporting community on twitter. In: Social, Cultural, and Behavioral Modeling: 9th International Conference, SBP-BRiMS 2016, Washington, DC, USA, June 28-July 1, 2016, Proceedings 9, pp. 346–355. Springer

  • Berger JM, Morgan J (2015) The ISIS twitter census: defining and describing the population of ISIS supporters on twitter. Brook Project US Relations Islamic World 3(20):1–42529

    Google Scholar 

  • Berger J, Strathearn B (2013) Who matters online: Measuring influence, evaluating content and countering violent extremism in online social networks

  • Bolsover G, Howard P (2017) Computational propaganda and political big data: Moving toward a more critical research agenda. Mary Ann Liebert, Inc. 140 Huguenot Street, 3rd Floor New Rochelle, NY 10801 USA

  • Brooking ET (2015) Anonymous vs. The Islamic State. https://foreignpolicy.com/2015/11/13/anonymous-hackers-islamic-state-isis-chan-online-war. [Online; accessed 10-January-2022]

  • Chu Z, Gianvecchio S, Wang H, Jajodia S (2012) Detecting automation of twitter accounts: Are you a human, bot, or cyborg? IEEE Trans Dependable Secure Comput 9(6):811–824

    Article  Google Scholar 

  • Comito C (2021) How covid-19 information spread in us? The role of twitter as early indicator of epidemics. IEEE Trans Serv Comput 15(3):1193–1205

    Article  Google Scholar 

  • Corera G (2020) ISIS ’still evading detection on Facebook’, report says. https://www.bbc.com/news/technology-53389657. [Online; accessed 23-February-2023]

  • Dalton A, Aghaei E, Al-Shaer E, Bhatia A, Castillo E, Cheng Z, Dhaduvai S, Duan Q, Hebenstreit B, Islam MM, et al(2020) Active defense against social engineering: The case for human language technology. In: Proceedings for the First International Workshop on Social Threats in Online Conversations: Understanding and Management, pp. 1–8

  • Darwish MA (2019) From Telegram to Twitter: The Lifecycle of Daesh Propaganda Material. https://www.voxpol.eu/from-telegram-to-twitter-the-lifecycle-of-daesh-propaganda-material. [Online; accessed 13-January-2022]

  • Farrall L (2019) The fall of the ISIS ‘caliphate’. https://www.cnn.com/2023/02/17/politics/us-troops-wounded-syria-isis/index.html. [Online; accessed 22-February-2023]

  • Fernandez M, Alani H (2018) Contextual semantics for radicalisation detection on twitter. In: Semantic Web for Social Good Workshop (SW4SG) at International Semantic Web Conference 2018, vol. 2182. CEUR Workshop Proceedings

  • Ferrara E, Wang W-Q, Varol O, Flammini A, Galstyan A (2016) Predicting online extremism, content adopters, and interaction reciprocity. In: Social Informatics: 8th International Conference, SocInfo 2016, Bellevue, WA, USA, November 11-14, 2016, Proceedings, Part II 8, pp. 22–39. Springer

  • Gaikwad M, Ahirrao S, Phansalkar S, Kotecha K (2021) Online extremism detection: a systematic literature review with emphasis on datasets, classification techniques, validation methods, and tools. IEEE Access 9:48364–48404

    Article  Google Scholar 

  • Grave E, Bojanowski P, Gupta P, Joulin A, Mikolov T (2018) Learning word vectors for 157 languages. In: Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018)

  • Hern A (2015) Anonymous ’at war’ with Isis, hacktivist group confirms. https://www.theguardian.com/technology/2015/nov/17/anonymous-war-isis-hacktivist-group-confirms. [Online; accessed 10-January-2022]

  • He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  • How to detect propaganda (1938) In Publications of the Institute for Propaganda Analysis, 210–218

  • Hristakieva K, Cresci S, Da San Martino G, Conti M, Nakov P (2022) The spread of propaganda by coordinated communities on social media. In: 14th ACM Web Science Conference 2022, pp. 191–201

  • International Assoc of Chiefs of Policec. IA, of Operations B, Research of America US. (1975) Clandestine tactics and technology-a technical and background intelligence data service, volume 3

  • Karimi Y, Squicciarini A, Wilson S (2022) Automated detection of doxing on twitter. Proc ACM Hum-Comput Interact 6(CSCW2):1–24

    Article  Google Scholar 

  • Karimi Y, Squicciarini A, Forster PK, Leavitt KM (2022) A longitudinal dataset of twitter isis users. arXiv preprint arXiv:2202.00878

  • Krizhevsky A (2014) One weird trick for parallelizing convolutional neural networks. arXiv preprint arXiv:1404.5997

  • Liebermann O (2023) 4 US troops wounded in Syria raid that killed senior ISIS leader on Thursday. https://www.cnn.com/2023/02/17/politics/us-troops-wounded-syria-isis/index.html. [Online; accessed 22-February-2023]

  • Lotan G, Graeff E, Ananny M, Gaffney D, Pearce I et al (2011) The Arab spring\(\vert\) the revolutions were tweeted: information flows during the 2011 Tunisian and Egyptian revolutions. Int J Commun 5:31

    Google Scholar 

  • Magdy W, Darwish K, Weber I (2015) # failedrevolutions: Using twitter to study the antecedents of isis support. arXiv preprint arXiv:1503.02401

  • Martino GDS, Yu S, Barrón-Cedeño A, Petrov R, Nakov P (2019) Fine-grained analysis of propaganda in news articles. arXiv preprint arXiv:1910.02517

  • McMinimy K, Winkler CK, Lokmanoglu AD, Almahmoud M (2021) Censoring extremism: influence of online restriction on official media products of isis. Terrorism and Political Violence, 1–17

  • Mehrotra S, Squicciarini AC, Serra E, Karimi Y (2022) Covid-19 and haters-a user model perspective. In: 2022 IEEE 9th international conference on data science and advanced analytics (DSAA), pp. 1–9. IEEE

  • Meleagrou-Hitchens A, Hughes S (2017) The threat to the united states from the islamic state’s virtual entrepreneurs. CTC Sentinel 10(3):1–8

    Google Scholar 

  • Moussaoui M, Zaghdoud M, Akaichi J (2019) A possibilistic framework for the detection of terrorism-related twitter communities in social media. Concurr Compu: Pract Exp 31(13):5077

    Article  Google Scholar 

  • Murugan P, Karimi Y, Squicciarini A, Griffin C (2021) Modeling longitudinal behavior dynamics among extremist users in twitter data. In: 2021 IEEE international conference on big data (Big Data), pp 4906–4914. IEEE

  • Office GP (2016) ISIS Online: Countering Terrorist Radicalization and Recruitment on the Internet and Social Media. https://www.gpo.gov/fdsys/pkg/CHRG-114shrg22476/content-detail.html. [Online; accessed 9-January-2022]

  • Rasheed A (2021) Turkish intelligence helped Iraq capture Islamic State leader, sources say. https://www.reuters.com/world/middle-east/exclusive-turkish-intelligence-helped-iraq-capture-islamic-state-leader-sources-2021-10-12. [Online; accessed 22-February-2023]

  • Rashkin H, Choi E, Jang JY, Volkova S, Choi Y (2017) Truth of varying shades: Analyzing language in fake news and political fact-checking. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2931–2937

  • Saif H, Dickinson T, Kastler L, Fernandez M, Alani H (2017) A semantic graph-based approach for radicalisation detection on social media. In: The Semantic Web: 14th International Conference, ESWC 2017, Portorož, Slovenia, May 28–June 1, 2017, Proceedings, Part I 14, pp. 571–587. Springer

  • Smith H (2015) Shocking images of drowned Syrian boy show tragic plight of refugees. https://www.theguardian.com/world/2015/sep/02/shocking-image-of-drowned-syrian-boy-shows-tragic-plight-of-refugees. [Online; accessed 26-December-2021]

  • Starbird K, Palen L (2012) (how) will the revolution be retweeted?: information diffusion and the 2011 egyptian uprising. In: Proceedings of the Acm 2012 conference on computer supported cooperative work, pp 7–16. ACM

  • Tan R (2017) Terrorists’ love for Telegram, explained. https://www.vox.com/world/2017/6/30/15886506. [Online; accessed 21-May-2023]

  • Tribe F (2015) How ISIS Uses Twitter. https://www.kaggle.com/fifthtribe/how-isis-uses-twitter. [Online; accessed 9-January-2022]

  • Vidino L, Hughes S (2015) ISIS in America: From Retweets to Raqqa (George Washington University: Program on Extremism, 2015) 7

  • Weirman S, Alexander A (2020) Hyperlinked sympathizers: Urls and the islamic state. Stud Conflict Terrorism 43(3):239–257

    Article  Google Scholar 

  • Wolfgang B (2021) Pentagon ramps up attacks on resurgent ISIS: ‘It is not defeated’. https://www.washingtontimes.com/news/2021/apr/6/pentagon-ramps-attacks-resurgent-isis-it-not-defea. [Online; accessed 26-February-2023]

  • Yu S, Di Pietro R, Nakov P (2020) A survey on computational propaganda detection

  • Zhang J, Zhang R, Zhang Y, Yan G (2016) The rise of social botnets: attacks and countermeasures. IEEE Trans Dependable Secure Comput 15(6):1068–1082

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgements

This work was funded by the National Science Foundation under grant number 1909255.

Author information

Authors and Affiliations

  1. College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802, USA

    Younes Karimi, Anna Squicciarini & Peter Kent Forster

Authors
  1. Younes Karimi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Anna Squicciarini
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Peter Kent Forster
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Younes Karimi.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Karimi, Y., Squicciarini, A. & Forster, P.K. A longitudinal dataset and analysis of Twitter ISIS users and propaganda. Soc. Netw. Anal. Min. 14, 19 (2024). https://doi.org/10.1007/s13278-023-01177-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13278-023-01177-7

Keywords

Search

Navigation