Elamur Research⌕
☰
home / papers / 2018 / ISIS at its apogee: the Arabic discourse on Twitter and what we can learn from that about ISIS support and Foreign Fighters

ISIS at its apogee: the Arabic discourse on Twitter and what we can learn from that about ISIS support and Foreign Fighters

Paper · 2018 · A. Ceron, L. Curini and S.M. Iacus

Summary

The authors ask how much backing the Islamic State received in Arabic-language Twitter conversation at the height of its territorial power, what moved that backing up or down, and whether online mood relates to real-world recruitment. They collected 26.2 million Arabic tweets about ISIS posted between July 2014 and January 2015. Instead of labelling each tweet, they used a supervised aggregated sentiment analysis method that estimates the proportions of supportive and hostile messages. They then ran statistical models in two directions. Over time, daily support was regressed on events such as military developments, the kind of target ISIS hit, the volume of discussion, and media coverage. Across countries, geolocated sentiment was compared with counts of foreign fighters. Support fell when ISIS harmed fellow Muslims. Countries with weaker online support sent more fighters. The authors call this pattern a "loneliness effect" and argue that censoring extremist talk could, against intuition, push isolated sympathisers toward radicalisation.

Key points

  • The corpus contains 26.2 million Arabic tweets from July 2014 to January 2015, the period of ISIS's peak expansion. Arabic was chosen because pro-ISIS accounts post in it more than 90% of the time, citing Siegel and Tucker 2017.
  • The method is supervised aggregated sentiment analysis. It measures the share of positive versus negative comments at the aggregate level rather than per tweet.
  • Daily support shifted with four drivers: whom ISIS targeted, military events, how much ISIS was discussed online, and media attention. Attacks on rival mosques and imams that killed Muslims lowered support.
  • There is a robust negative cross-country link between pro-ISIS sentiment and the number of foreign fighters. This "loneliness effect" survives several alternative checks.
  • The authors acknowledge an ecological-fallacy risk because all inference is at the aggregate level. Policy context includes Anonymous shutting about 5,000 pro-ISIS accounts and roughly 5,600 returning fighters from 33 countries by late 2017.

Interesting ideas

  • I1. The study estimates the distribution of stances in a corpus directly instead of summing noisy per-item labels, which avoids carrying individual classification errors into the totals.
  • I2. A text-derived daily signal is aligned with a dated external event log, so that changes in opinion can be explained by specific happenings.
  • I3. The paper finds that approval of an actor depends on who the victim is: harming in-group members draws backlash, while harming out-group targets does not.
  • I4. The authors check an online measure against an independent offline outcome and state openly what aggregate data cannot show.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (learn): Evaluation could compare corpus-level shares of relation types or frame types between silver data and gold data, catching systematic drift that per-sentence accuracy hides.
  • I2 (world): The world of a text could keep evaluative states as time-indexed values tied to the ordered event list, so that an answer to "why did attitude change" points to a concrete preceding event.
  • I3 (frames): Stance inference in prag could combine the agent and patient roles with the reader community's group membership instead of treating a violent verb as uniformly negative.
  • I4 (learn): Mova's derived signals could be validated against external ground truth, with explicit notes on which conclusions hold only in aggregate, as a complement to negative controls.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of MilanMilan · Italy6 works · 38,727 citations

 Fields, topics and concepts

📚 Shelves 3The field of science this work belongs to (OpenAlex fields).Social Sciences · 1,772 worksSociology and Political Science · 577 worksCommunication · 97 works

🧭 Topics 2Research subjects and languages the work is about.Semitic languages · 2,908 worksDiscourse analysis · 466 works

Cite

Cite as A. Ceron, L. Curini and S.M. Iacus. 2018. ISIS at its apogee: the Arabic discourse on Twitter and what we can learn from that about ISIS support and Foreign Fighters. arXiv:1804.04059.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.1804.04059 · arXiv 1804.04059

@misc{ceron2018isis,
  title = {{ISIS at its apogee: the Arabic discourse on Twitter and what we can learn from that about ISIS support and Foreign Fighters}},
  author = {A. Ceron, L. Curini and S.M. Iacus},
  year = {2018},
  doi = {10.48550/arxiv.1804.04059},
  eprint = {1804.04059},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1804.04059}
}

References

59 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Akhgar, Babak, Bayerl, P. Saskia, and Sampson, Fraser (2016). Open Source Intelligence Investigation. Springer. Al-Moslmi, T., Albaredm Adel Al-Shabi. find
  2. M., Omar, N., and Abdullah, S. (2017). Arabic senti-lexicon: Constructing publicly available language resources for Arabic sentiment analysis, Journal of Information Science, DOI: 10.1177/0165551516683 ↗
  3. Al-Rawi, A. (2017). Online political activism in Syria: Sentiment analysis of social media. Sage Research Studies Cases, 1-25. ↗
  4. Badawy, A., & Ferrara, E. (2018). The Rise of Jihadist Propaganda on Social Networks. Journal of Computational Social Science, https://doi.org/10.1007/s42001-018-0015-z ↗
  5. Barrett, Richard (2017). Beyond the Caliphate: Foreign Fighters and the Threat of Returnees, The Soufan Group 5 find
  6. Benson D (2014) Why the Internet is not increasing terrorism. Security Studies 23(2): 293–328. ↗
  7. Berger, J.M. and Jonathon Morgan (2015). The ISIS Twitter Census. Defining and describing the population of ISIS supporters on Twitter, The Brookings Project on U.S. Relations with the Islamic World, Analysis Paper, No. 20, March 2015 find
  8. Berinsky, Adam J. (1999). The Two Faces of Public Opinion, American Journal of Political Science, 43(4): 1209-1230 find
  9. Bishop, G.F. (2003). Intelligent design: Illusions of an informed public. Public Perspective, 14(3): 5-Brands, Hal, and Peter Feaver (2017). Trump and Terrorism: U.S. Strategy After ISIS. Foreign Affairs 96: 28-36 - 22 - Briggs, Rachel (2010). Hearts and minds and votes: the role of democratic participation in countering terrorism. Democratization 17(2): 272-285. find
  10. Burgoon, Brian (2006). On Welfare and Terror: Social Welfare Policies and Political-Economic Roots of Terrorism. Journal of Conflict Resolution 50(2): 176-203 find
  11. Burnap, P. abd Williams, M.L. (2015) Cyber Hate Speech on Twitter: An Application of Machine Classification and Statistical Modelling for Policy and Decision Making, Policy & Internet 7(2): 223-242. find
  12. Byman, Daniel (2016). ISIS Goes Global: Fight the Islamic State by Targeting Its Affiliates. Foreign Affairs 95: 76-85. find
  13. Carter, Joseph A, Shiraz Maher and Peter R Neumann. 2014. # Greenbirds: Measuring Importance and Influence in Syrian Foreign Fighter Networks. The International Centre For the Study of Radicalisation and Political Violence. find
  14. Ceron, Andrea, Luigi Curini, and Stefano Iacus (2016). iSA: a fast, scalable and accurate algorithm for sentiment analysis of social media content. Information Sciences 367–368: 105–124 ↗
  15. Cohen, Jared (2015). Digital counterinsurgency: How to marginalize the Islamic State online. Foreign Affairs 94 (6): 52–58. find
  16. Cox, Joseph (2015). ISIS now has a propaganda site on the dark web. Motherboard. Available from http://motherboard.vice.com, 16 November 2015. ↗
  17. Cronin, Audrey Kurth (2009). How Terrorism Ends: Understanding the Decline and Demise of Terrorist Campaigns. Princeton, NJ: Princeton University Press Cunliffe, Emma and Luigi Curini (2018). ISIS and heritage destruction: A sentiment analysis. Antiquity. A Review of World Archaeology, forthcoming Dalacoura, Katerina (2006). Islamist Terrorism and the Middle East Democratic Deficit: Political Exclusion, Repression and the Causes of Extremism. Democratization 13(3): 508-525. - 23 - DiGrazia J, McKelvey K, Bollen J, Rojas F (2013) More Tweets, More Votes: Social Media as a Quantitative Indicator of Political doi:10.1371/journal.pone.0079449 ↗
  18. Efron, B., Tibshirani, R. (1993). An Introduction to the Bootstrap, Boca Raton, FL, Chapman & Hall/CRC,CRC press. el-Nawawy, M., and S. Khamis (2009). Islam Dot Com: Contemporary Islamic Discourses in Cyberspace. New York: Palgrave Macmillan. find
  19. Farwell, James P. (2014). The Media Strategy of ISIS. Survival 56(6): 49-55 ↗
  20. Ferrara, E. (2017). Contagion dynamics of extremist propaganda in social networks. Information Sciences, 418, 1-12. ↗
  21. Ferrara E., Wang WQ., Varol O., Flammini A., Galstyan A. (2016) Predicting Online Extremism, Content Adopters, and Interaction Reciprocity. In: Spiro E., Ahn YY. (eds) Social Informatics. find
  22. SocInfo 2016. Lecture Notes in Computer Science, vol 10047. find
  23. Springer, Cham Fisher, R.J. (1993). Social desirability bias and the validity of indirect questioning. Journal of Consumer Research, 20(2), 303–315. ↗
  24. Frey, Bruno S., and Simon Luechinger (2003). How to Fight Terrorism: Alternatives to Deterrence. Defense and Peace Economics 14(4): 237-249. ↗
  25. Gartenstein-Ross, D., Barr, N. and B. Moreng. (2016). “The Islamic State’s Global Propaganda Strategy”, The International Centre for Counter-Terrorism – The Hague 7, no. 1 . [Online]. 31 st March. Available from: https://icct.nl/publication/the-islamic-states-global-propaganda-strategy/González-Bailón, ↗
  26. Sandra, Wang, Ning, Rivero, Alejandro, Borge-Holthoeferd, Javier, and Moreno, Yamir (2014). Assessing the bias in samples of large online networks, Social Networks, 38, 16-27 Behavior. PLoS ONE 8(11): e79449. - 24 - Greenberg, Karen J. (2016). Counter-Radicalization via the Internet. The ANNALS of the American Academy of Political and Social Science 668(1): 165-179. find
  27. Grimmer, Justin, and Stewart, Brandon M. (2013). Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts. Political Analysis, 21(3): 267-297. ↗
  28. Gurr, Ted Robert (2006). Economic Factors. In Louise Richardson (ed.) The Roots of Terrorism, 85-102. New York, NY: Taylor & Francis. find
  29. Hashemi, N. and Postel, D. (2017). Sectarianization: Mapping the New Politics of the Middle East. The Review of Faith & International Affairs, 15(3), 1-13. ↗
  30. Hassan H. (2016). The Sectarianism of the Islamic State: Ideological Roots and Political Context, Carnegie Endowment For http://carnegieendowment.org/2016/06/13/sectarianism-of-islamic-state-ideological-roots-and-political-context-pub-63746 [Accessed 22 Dec. 2017]. ↗
  31. Hirschman, Albert O. (1970). Exit, Voice, and Loyalty: Responses to Decline in Firms, Organizations, and States. Cambridge, MA: Harvard University Press Hopkins, D., and King, G. (2010). A method of automated nonparametric content analysis for social science. American Journal of Political Science, 54(1), 229–247. find
  32. Howard, P.N., and Hussain, M.M. (2011). The role of digital media. Journal of Democracy, 22(3), 35–48. find
  33. Iacus, S. M., King, G., Porro, G. (2011) ‘Multivariate matching methods that are monotonic imbalance bounding’, Journal of the American Statistical Association, 106: 345-361. ↗
  34. Jamal, Amaney A., Robert O. Keohane, David Romney and Dustin Tingley (2015). Anti Americanism and Anti Interventionism in Arabic Twitter Discourses, Perspectives on Politics, 13(1), 55-73 International Peace. Available from: - 25 - Jenkins, Brian (1981). The Psychological Implications of Media-Covered Terrorism. find
  35. Rand Corporation Jurgens, David. 2013. “That’s What Friends Are For: Inferring Location in Online Social Media Platforms Based on Social Relationships.” ICWSM 13:273–282. find
  36. King, G., Pan, J., & Roberts, M.E. (2013). How censorship in China allows government criticism but silences collective expression. American Political Science Review, 107(2), 326–343. ↗
  37. King, Gary, Pan, Jennifer, and Roberts, Margaret E. (2014). Reverse Engineering Chinese Censorship: Randomized Experimentation and Participant Observation, Science 345 (6199): 1-10 find
  38. Klausen, Jytte (2015). Tweeting the Jihad: Social Media Networks of Western Foreign Fighters in Syria and Iraq, Studies in Conflict & Terrorism, 38:1, 1-22 find
  39. Knopf, Jeffrey W. (2010). The Fourth Wave in Deterrence Research. Contemporary Security Policy 31(1): 1-33. ↗
  40. Kraidy, Marwan M (2017). The projectilic image: Islamic State’s digital visual warfare and global networked affect. Media, Culture & Society 39(8): 1194-1209. ↗
  41. Lichbach, Mark Irving (1987). Deterrence or Escalation? The Puzzle of aggregate Studies of Repression and Dissent. The Journal of Conflict Resolution 31(2): 266-297. ↗
  42. Lu, Z., Wu, X., Bongard, J. C. (2015). Active learning through adaptive heterogeneous ensembling, IEEE Trans. Knowl. Data Eng, 27(2): 368-381. ↗
  43. Malik, S. (2014) ‘Support for Isis stronger in Arabic social media in Europe than in Syria, The Guardian, 28 November’. Available at: https://www.theguardian.com/world/2014/nov/28/support-isis-stronger-arabic-social-media-europe-us-than-syria ↗
  44. Mitts, Tamar (2017). From Isolation to Radicalization: Anti-Muslim Hostility and Support for ISIS in the West, SSRN Scholarly Paper. Rochester, NY: Social Science Research Network - 26 - Monroe, B.L., Pan, J., Roberts, M.E., Sen, M., and Sinclari, B. (2015). No! Formal Theory, Causal Inference, and Big Data Are Not Contradictory Trends in Political Science, PS: Political Science & Politics, 48(1), 71-74 ↗
  45. Mostafa, M. M. (2013). More than words: Social networks’ text mining for consumer brand sentiments, Expert Systems With Applications, 40(10): 4241–4251. ↗
  46. Nagler, Jonathan, Tucker, Joshua A. (2015). Drawing Inferences and Testing Theories with Big Data, PS: Political Science & Politics, 48(1), 84-88 find
  47. Neumann, Peter. 2013. Options and strategies for countering radicalization in the United States. Studies in Conflict and Terrorism 36(6): 431–59. find
  48. Nielsen, Richard Alexander (2013). The Lonely Jihadist: Weak Networks and the Radicalization of Muslim Clerics. Doctoral dissertation, https://dash.harvard.edu/bitstream/handle/1/11124850/Nielsen_gsas.harvard_0084L_10887.pdf?seq uence=1 ↗
  49. Novenario, Celine Marie I. (2016) Differentiating Al Qaeda and the Islamic State Through Strategies Publicized in Jihadist Magazines. Studies in Conflict & Terrorism, 39(11): 953-967. find
  50. O’Hara, Kieron and Stevens, David (2015). Echo Chambers and Online Radicalism: Assessing the Internet’s Complicity in Violent Extremism. Policy & Internet, 7(4): 401-422. ↗
  51. Siegel, Alexandra A. and Joshua A. Tucker (2017). The Islamic State’s information warfare. Measuring the success of ISIS’s online strategy. Journal of Language and Politics. doi 10.1075/jlp.17005.sieissn 1569–2159 ↗
  52. Stephens-Davidowitz, Seth I. (2013). The Cost of Racial Animus on a Black Presidential Candidate: Using Google Search Data to Find https://ssrn.com/abstract=2238851 or http://dx.doi.org/10.2139/ssrn.2238851 Harvard University, Available at: What Surveys Miss. Available at SSRN: - 27 - Torres Soriano, M (2012) The vulnerabilities of online terrorism. Studies in Conflict & Terrorism 35(4): 263–277. ↗
  53. Tucker, Joshua, Theocharis, Yannis, Roberts, Margaret, and Barberá, Pablo (2017). From Liberation to Turmoil: Social Media and Democracy. Journal of Democracy, 28(4): 46-59. ↗
  54. Yoon, S., Elhadad, N., and Bakken, S. (2013). A practical approach for content mining of tweets, American Journal of Preventive Medicine, 45(1): 122–129. find
  55. Weimann, Gabriel, and Conrad Winn. 1994. The Theatre of Terror: Mass Media and International Terrorism. New York, NY: Longman. find
  56. Whine, M (1999) Cyberspace. A new medium for communication, command, and control by extremists. Studies in Conflict & Terrorism 22(3): 231–245. find
  57. Wojcieszak, M. (2010). Don’t Talk to Me: Effects of Ideologically Homogeneous Online Groups and Politically Dissimilar Offline Ties on Extremism. New Media and Society 12 (4): 637–55. ↗
  58. Zeitzoff, Thomas (2011). Using Social Media to Measure Conflict Dynamics: An Application to the 2008-2009 Gaza Conflict, The Journal of Conflict Resolution, 55 (6), 938-969 find
  59. Zeitzoff, Thomas, John Kelly and Gilad Lotan (2015). Using social media to measure foreign policy dynamics: An empirical analysis of the Iranian–Israeli confrontation (2012–13), Journal of Peace Research, 52 (3), 368–383 Figures Figure 1: Daily variation around the share of positive sentiment mean towards ISIS’s actions (variable name: SENTIMENT DEVIATION) - 28 - .6 .4 .2 -.2 01jul2014 01sep2014 SENTIMENT DEVIATION Figure 2: Daily variation around the average number of tweets discussing ISIS (variable name: ATTENTION DEVIATION) 01nov2014 01jan2015 Day Lowess Function - 29 - 01jul2014 01sep2014 ATTENTION DEVIATION 01nov2014 01jan2015 Day Lowess Function - 30 - Figure 3: Predicted number of Foreign Fighters for different values of Sentiment toward ISIS Predicted # Foreign Fighters 500 1000 .1 .2 .3 .4 .5 .6 .7 Sentiment toward ISIS source: Model 1, Table 3 Tables Table 1: Examples of classified tweets about ISIS in the training-set Positive classification find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ceron-2018-isis-apogee-arabic-discourse-twitter/