Investigating the effect of combining GRU neural networks with handcrafted features for religious hatred detection on Arabic Twitter space

  • Nuha AlbadiEmail author
  • Maram Kurdi
  • Shivakant Mishra
Original Article


Religious hatred is a serious problem on Arabic Twitter space and has the potential to ignite terrorism and hate crimes beyond cyber space. To the best of our knowledge, this is the first research effort investigating the problem of recognizing Arabic tweets using inflammatory and dehumanizing language to promote hatred and violence against people on the basis of religious beliefs. In this work, we create the first public Arabic dataset of tweets annotated for religious hate speech detection. We also create three public Arabic lexicons of terms related to religion along with hate scores. We then present a thorough analysis of the labeled dataset, reporting most targeted religious groups and hateful and non-hateful tweets’ country of origin. The labeled dataset is then used to train seven classification models using lexicon-based, n-gram-based, and deep-learning-based approaches. These models are evaluated on new unseen dataset to assess the generalization ability of the developed classifiers. While using Gated Recurrent Units with pre-trained word embeddings provides best precision (0.76) and \(F_1\) score (0.77), training that same neural network on additional temporal, users, and content features provides the state-of-the-art performance in terms of recall (0.84).


Cyberhate Religious hate speech Online radicalization Social media mining Arabic NLP Twitter data analysis 



  1. Al-garadi MA, Varathan KD, Ravana SD (2016) Cybercrime detection in online communications: the experimental case of cyberbullying detection in the twitter network. Comput Hum Behav 63:433–443CrossRefGoogle Scholar
  2. Al-Twairesh N, Al-Khalifa H, AlSalman A (2016) Arasenti: large-scale twitter-specific Arabic sentiment lexicons. In: Proceedings of the 54th annual meeting of the association for computational linguistics (volume 1: long papers), vol 1, pp 697–705Google Scholar
  3. Albadi N, Kurdi M, Mishra S (2018) Are they our brothers? Analysis and detection of religious hate speech in the Arabic Twittersphere. In: 2018 IEEE/ACM international conference on advances in social networks analysis and mining (ASONAM). IEEE, pp 69–76Google Scholar
  4. Badjatiya P, Gupta S, Gupta M, Varma V (2017) Deep learning for hate speech detection in tweets. In: Proceedings of the 26th international conference on world wide web companion. International World Wide Web Conferences Steering Committee, pp 759–760Google Scholar
  5. Burton SH, Tanner KW, Giraud-Carrier CG, West JH, Barnes MD (2012) “right time, right place” health communication on twitter: value and accuracy of location information. J Med Internet Res 14(6):e156CrossRefGoogle Scholar
  6. Chatzakou D, Kourtellis N, Blackburn J, De Cristofaro E, Stringhini G, Vakali A (2017) Mean birds: detecting aggression and bullying on twitter. In: Proceedings of the 2017 ACM on web science conference. ACM, pp 13–22Google Scholar
  7. Chong A (2006) Intolerance of terror, or the terror of intolerance-religious tolerance and the response to terrorism. UTS L Rev 8:153Google Scholar
  8. Chung J, Gülçehre Ç, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR, arXiv:abs/1412.3555
  9. Church KW, Hanks P (1990) Word association norms, mutual information, and lexicography. Comput Linguist 16(1):22–29Google Scholar
  10. Darwish K, Magdy W, Mourad A (2012) Language processing for Arabic microblog retrieval. In: Proceedings of the 21st ACM international conference on Information and knowledge management. ACM, pp 2427–2430Google Scholar
  11. Davidson T, Warmsley D, Macy M, Weber I (2017) Automated hate speech detection and the problem of offensive language. In: Proceedings of the 11th international AAAI conference on web and social media. ICWSM ’17, pp 512–515Google Scholar
  12. Djuric N, Zhou J, Morris R, Grbovic M, Radosavljevic V, Bhamidipati N (2015) Hate speech detection with comment embeddings. In: Proceedings of the 24th international conference on world wide web. ACM, pp 29–30Google Scholar
  13. Duwairi RM, Marji R, Sha’ban N, Rushaidat S (2014) Sentiment analysis in Arabic tweets. In: 2014 5th international conference on information and communication systems (ICICS). IEEE, pp 1–6Google Scholar
  14. Forman G (2003) An extensive empirical study of feature selection metrics for text classification. J Mach Learn Res 3:1289–1305zbMATHGoogle Scholar
  15. Forman G (2008) Bns feature scaling: an improved representation over tf-idf for svm text classification. In: Proceedings of the 17th ACM conference on information and knowledge management. ACM, pp 263–270Google Scholar
  16. Founta AM, Chatzakou D, Kourtellis N, Blackburn J, Vakali A, Leontiadis I (2019) A unified deep learning architecture for abuse detection. In: Proceedings of the 10th ACM conference on web science. ACM, pp 105–114Google Scholar
  17. Gitari ND, Zuping Z, Damien H, Long J (2015) A lexicon-based approach for hate speech detection. Int J Multimed Ubiquitous Eng 10(4):215–230CrossRefGoogle Scholar
  18. Gouws S, Metzler D, Cai C, Hovy E (2011) Contextual bearing on linguistic variation in social media. In: Proceedings of the workshop on languages in social media. Association for Computational Linguistics, pp 20–29Google Scholar
  19. Kaati L, Omer E, Prucha N, Shrestha A (2015) Detecting multipliers of jihadism on twitter. In: 2015 IEEE international conference on data mining workshop (ICDMW). IEEE, pp 954–960Google Scholar
  20. Kaji N, Kitsuregawa M (2007) Building lexicon for sentiment analysis from massive collection of html documents. In: Proceedings of the 2007 joint conference on empirical methods in natural language processing and computational natural language learning (EMNLP-CoNLL)Google Scholar
  21. Kulshrestha J, Kooti F, Nikravesh A, Gummadi KP (2012) Geographic dissection of the twitter network. In: Sixth international AAAI conference on weblogs and social media. AAAIGoogle Scholar
  22. Kwok I, Wang Y (2013) Locate the hate: detecting tweets against blacks. In: AAAIGoogle Scholar
  23. Larsen ME, Boonstra TW, Batterham PJ, O’Dea B, Paris C, Christensen H (2015) We feel: mapping emotion on twitter. IEEE J Biomed Health Inform 19(4):1246–1252CrossRefGoogle Scholar
  24. Le Q, Mikolov T (2014) Distributed representations of sentences and documents. In: International conference on machine learning, pp 1188–1196Google Scholar
  25. Magdy W, Darwish K, Abokhodair N, Rahimi A, Baldwin T (2016a) # isisisnotislam or# deportallmuslims? Predicting unspoken views. In: Proceedings of the 8th ACM conference on web science. ACM, pp 95–106Google Scholar
  26. Magdy W, Darwish K, Weber I (2016b) # failedrevolutions: using twitter to study the antecedents of ISIS support. First Monday 21(2)Google Scholar
  27. Mohammad SM, Kiritchenko S (2015) Using hashtags to capture fine emotion categories from tweets. Comput Intell 31(2):301–326MathSciNetCrossRefGoogle Scholar
  28. Mohammad SM, Kiritchenko S, Zhu X (2013) Nrc-canada: building the state-of-the-art in sentiment analysis of tweets. In: Proceedings of the seventh international workshop on semantic evaluation exercises (SemEval-2013), Atlanta, Georgia, USAGoogle Scholar
  29. Mubarak H, Darwish K, Magdy W (2017) Abusive language detection on Arabic social media. In: Proceedings of the first workshop on abusive language online, pp 52–56Google Scholar
  30. Müller K, Schwarz C, et al. (2018) Fanning the flames of hate: social media and hate crime. Technical reports. Competitive Advantage in the Global Economy (CAGE)Google Scholar
  31. Olteanu A, Castillo C, Diaz F, Vieweg S (2014) Crisislex: a lexicon for collecting and filtering microblogged communications in crises. In: ICWSMGoogle Scholar
  32. Pasha A, Al-Badrashiny M, Diab MT, El Kholy A, Eskander R, Habash N, Pooleery M, Rambow O, Roth R (2014) Madamira: a fast, comprehensive tool for morphological analysis and disambiguation of Arabic. LREC 14:1094–1101Google Scholar
  33. Pearson K (1900) X on the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. Lond Edinb Dublin Philos Mag J Sci 50(302):157–175CrossRefGoogle Scholar
  34. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830MathSciNetzbMATHGoogle Scholar
  35. Pew Research Center, Washington, DC (2009) Mapping the global Muslim population. Accessed 24 October 2018
  36. Pew Research Center, Washington, DC (2015) Religious composition by country, 2010–2050. Accessed 24 October 2018
  37. Pew Research Center, Washington, DC (2017) Global restrictions on religion rise modestly in 2015, reversing downward trend - appendix b: social hostilities index. Accessed 24 October 2018
  38. Ribeiro MH, Calais PH, Santos YA, Almeida VA, Meira Jr W (2018) Characterizing and detecting hateful users on twitter. In: Twelfth international AAAI conference on web and social mediaGoogle Scholar
  39. Salem F (2017) Social media and the internet of things towards data-driven policymaking in the Arab world: potential, limits and concerns. MBR School of Government 7, DubaiGoogle Scholar
  40. Silva LA, Mondal M, Correa D, Benevenuto F, Weber I (2016) Analyzing the targets of hate in online social media. In: Proceedings of the 11th international AAAI conference on web and social media. ICWSM’16, pp 687–690Google Scholar
  41. Soliman AB, Eissa K, El-Beltagy SR (2017) Aravec: a set of Arabic word embedding models for use in Arabic NLP. Proc Comput Sci 117:256–265CrossRefGoogle Scholar
  42. Taghva K, Elkhoury R, Coombs J (2005) Arabic stemming without a root dictionary. In: International conference on information technology: coding and computing, 2005, ITCC 2005. IEEE, vol 1, pp 152–157Google Scholar
  43. Twitter Safety (2017) Enforcing new rules to reduce hateful conduct and abusive behavior. Accessed 27 November 2018
  44. Waseem Z, Hovy D (2016) Hateful symbols or hateful people? predictive features for hate speech detection on twitter. In: Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics—human language technologies. NAACL-HLT’16, pp 88–93Google Scholar
  45. Wiktorowicz Q, Amanullah S (2015) How tech can fight extremism. Accessed 24 October 2018
  46. Yang J, Jiang YG, Hauptmann AG, Ngo CW (2007) Evaluating bag-of-visual-words representations in scene classification. In: Proceedings of the international workshop on multimedia information retrieval. ACM, pp 197–206Google Scholar

Copyright information

© Springer-Verlag GmbH Austria, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Taibah UniversityMedinaSaudi Arabia
  2. 2.Taif UniversityTaifSaudi Arabia
  3. 3.University of ColoradoBoulderUSA

Personalised recommendations