Detecting Hate Speech on Twitter Using a Convolution-GRU Based Deep Neural Network

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10843)


In recent years, the increasing propagation of hate speech on social media and the urgent need for effective counter-measures have drawn significant investment from governments, companies, and empirical research. Despite a large number of emerging scientific studies to address the problem, a major limitation of existing work is the lack of comparative evaluations, which makes it difficult to assess the contribution of individual works. This paper introduces a new method based on a deep neural network combining convolutional and gated recurrent networks. We conduct an extensive evaluation of the method against several baselines and state of the art on the largest collection of publicly available Twitter datasets to date, and show that compared to previously reported results on these datasets, our proposed method is able to capture both word sequence and order information in short texts, and it sets new benchmark by outperforming on 6 out of 7 datasets by between 1 and 13% in F1. We also extend the existing dataset collection on this task by creating a new dataset covering different topics.



Part of this work was conducted during the SPUR project funded by the Nottingham Trent University. We also thank Qian Wang, a student funded by the Nuffield Foundation for data analysis in this work.


  1. 1.
    Badjatiya, P., Gupta, S., Gupta, M., Varma, V.: Deep learning for hate speech detection in tweets. In: Proceedings of the 26th International Conference on World Wide Web Companion, pp. 759–760 (2017)Google Scholar
  2. 2.
    BBCNews: Countering hate speech online. Accessed July 2017
  3. 3.
    BBCNews: Finsbury park attack: son of hire boss held over Facebook post. Accessed May 2017
  4. 4.
    Burnap, P., Williams, M.L.: Cyber hate speech on Twitter: an application of machine classification and statistical modeling for policy and decision making. Policy Internet 7(2), 223–242 (2015)CrossRefGoogle Scholar
  5. 5.
    Chiu, J.P., Nichols, E.: Named entity recognition with bidirectional LSTM-CNNs. Trans. Assoc. Comput. Linguist. 4, 357–370 (2016)Google Scholar
  6. 6.
    Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: NIPS 2014 Deep Learning and Representation Learning Workshop (2014)Google Scholar
  7. 7.
    Davidson, T., Warmsley, D., Macy, M., Weber, I.: Automated hate speech detection and the problem of offensive language. In: Proceedings of the 11th Conference on Web and Social Media. AAAI (2017)Google Scholar
  8. 8.
    Dinakar, K., Jones, B., Havasi, C., Lieberman, H., Picard, R.: Common sense reasoning for detection, prevention, and mitigation of cyberbullying. ACM Trans. Interact. Intell. Syst. 2(3), 18:1–18:30 (2012)CrossRefGoogle Scholar
  9. 9.
    Djuric, N., Zhou, J., Morris, R., Grbovic, M., Radosavljevic, V., Bhamidipati, N.: Hate speech detection with comment embeddings. In: Proceedings of the 24th International Conference on World Wide Web, pp. 29–30. ACM (2015)Google Scholar
  10. 10.
    Gambäck, B., Sikdar, U.K.: Using convolutional neural networks to classify hate-speech. In: Proceedings of the First Workshop on Abusive Language Online, pp. 85–90. Association for Computational Linguistics (2017)Google Scholar
  11. 11.
    Gitari, N.D., Zuping, Z., Damien, H., Long, J.: A lexicon-based approach for hate speech detection. Int. J. Multimed. Ubiquit. Eng. 10(10), 215–230 (2015)CrossRefGoogle Scholar
  12. 12.
    Guardian: Anti-muslim hate crime surges after Manchester and London Bridge attacks. Accessed July 2017
  13. 13.
    Guardian: Zuckerberg on refugee crisis: ‘hate speech has no place on Facebook’. Accessed July 2017
  14. 14.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference for Learning Representations (2015)Google Scholar
  15. 15.
    McCaffrey, J.D.: Why you should use cross-entropy error instead of classification error or mean squared error for neural network classifier training. Accessed Jan 2018
  16. 16.
    Mehdad, Y., Tetreault, J.: Do characters abuse more than words? In: Proceedings of the SIGDIAL 2016 Conference, Los Angeles, USA, pp. 299–303. Association for Computational Linguistics (2016)Google Scholar
  17. 17.
    Nobata, C., Tetreault, J., Thomas, A., Mehdad, Y., Chang, Y.: Abusive language detection in online user content. In: Proceedings of the 25th International Conference on World Wide Web, pp. 145–153 (2016)Google Scholar
  18. 18.
    Okeowo, A.: Hate on the rise after Trump’s election. Accessed July 2017
  19. 19.
    Ordóñez, F.J., Roggen, D.: Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1), 115 (2016)CrossRefGoogle Scholar
  20. 20.
    Park, J.H., Fung, P.: One-step and two-step classification for abusive language detection on Twitter. In: ALW1: 1st Workshop on Abusive Language Online, Vancouver, Canada. Association for Computational Linguistics (2017)Google Scholar
  21. 21.
    Schmidt, A., Wiegand, M.: A survey on hate speech detection using natural language processing. In: International Workshop on Natural Language Processing for Social Media, pp. 1–10. Association for Computational Linguistics (2017)Google Scholar
  22. 22.
    Tsironi, E., Barros, P., Weber, C., Wermter, S.: An analysis of convolutional long short-term memory recurrent neural networks for gesture recognition. Neurocomputing 268(C), 76–86 (2017)CrossRefGoogle Scholar
  23. 23.
    Vigna, F.D., Cimino, A., Dell’Orletta, F., Petrocchi, M., Tesconi, M.: Hate me, hate me not: hate speech detection on Facebook. In: Proceedings of the First Italian Conference on Cybersecurity, pp. 86–95 (2017)Google Scholar
  24. 24.
    Warner, W., Hirschberg, J.: Detecting hate speech on the world wide web. In: Proceedings of the Second Workshop on Language in Social Media, LSM 2012, pp. 19–26. Association for Computational Linguistics (2012)Google Scholar
  25. 25.
    Waseem, Z.: Are you a racist or am i seeing things? Annotator influence on hate speech detection on Twitter. In: Proceedings of the Workshop on NLP and Computational Social Science, pp. 138–142. Association for Computational Linguistics (2016)Google Scholar
  26. 26.
    Waseem, Z., Hovy, D.: Hateful symbols or hateful people? Predictive features for hate speech detection on Twitter. In: Proceedings of the NAACL Student Research Workshop, pp. 88–93. Association for Computational Linguistics (2016)Google Scholar
  27. 27.
    Xiang, G., Fan, B., Wang, L., Hong, J., Rose, C.: Detecting offensive tweets via topical feature discovery over a large scale Twitter corpus. In: Conference on Information and Knowledge Management, pp. 1980–1984. ACM (2012)Google Scholar
  28. 28.
    Zhong, H., Li, H., Squicciarini, A., Rajtmajer, S., Griffin, C., Miller, D., Caragea, C.: Content-driven detection of cyberbullying on the Instagram social network. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI 2016, pp. 3952–3958. AAAI Press (2016)Google Scholar
  29. 29.
    Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. Roy. Stat. Soc. Ser. B Stat. Methodol. 67(2), 301–320 (2005)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.University of SheffieldSheffieldUK
  2. 2.Nottingham Trent UniversityNottinghamUK

Personalised recommendations