Automatic Extraction of Harmful Sentence Patterns with Application in Cyberbullying Detection

  • Michal PtaszynskiEmail author
  • Fumito Masui
  • Yasutomo Kimura
  • Rafal Rzepka
  • Kenji Araki
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10930)


The problem of humiliating and slandering people through Internet, generally defined as cyberbullying (later: CB), has been recently noticed as a serious social problem disturbing mental health of Internet users. In Japan, to deal with the problem, members of Parent-Teacher Association (PTA) perform Internet Patrol – a voluntary work by reading through the whole Web contents to spot cyberbullying entries. To help PTA members we propose a novel method for automatic detection of malicious contents on the Internet. The method is based on a brute force search algorithm-inspired combinatorial approach to language modeling. The method automatically extracts sophisticated sentence patterns and uses them in classification. We tested the method on actual data containing cyberbullying provided by Human Rights Center. The results show our method outperformed previous methods. It is also more efficient as it requires minimal human effort.


Cyberbullying detection Natural language processing Pattern extraction 


  1. 1.
    Belsey, B.: Cyberbullying: An Emerging Threat for the “Always On” Generation (2007). Presentation_ Description.pdf
  2. 2.
    Fujii, Y., Ando, S., Ito, T.: Yūgai jōhō firutaringu no tame no 2-tango-kan no kyori oyobi kyōki jōhō ni yoru bunshō bunrui shuhō no teian (Developing a method based on 2-word co-occurence information for filtering harmful information). In: Proceedings of the 24th Annual Conference of The Japanese Society for Artificial Intelligence (JSAI2010), paper ID: 3D2-4, pp. 1–4 (2010). (in Japanese)Google Scholar
  3. 3.
    Hatakeyama, S., Masui, F., Ptaszynski, M., Yamamoto, K.: Improving performance of cyberbullying detection method with double filtered point-wise mutual information. In: Demo Session of the 2015 ACM Symposium on Cloud Computing 2015 (ACM-SoCC 2015), Kohala Coast, Hawaii, 27–29 August 2015Google Scholar
  4. 4.
    Hashimoto, H., Kinoshita, T., Harada, M.: Firutaringu no tame no ingo no yūgai goi kenshutsu kinō no imi kaiseki shisutemu SAGE e no kumikomi (Implementing a function for filtering harmful slang words into the semantic analysis system SAGE), IPSJ SIG Notes 2010-SLP-81(14), pp. 1–6 (2010). (in Japanese)Google Scholar
  5. 5.
    Hinduja, S., Patchin, J.W.: Bullying Beyond the Schoolyard: Preventing and Responding to Cyberbullying. Corwin Press, Thousand Oaks (2009)Google Scholar
  6. 6.
    Ikeda, K., Yanagihara, T.: Kakuyōso no chūshōka ni motozuku ihō-, yūgai-bunsho kenshutsu shuhō no teian to hyōka (Proposal and evaluation of a method for illegal and harmful document detection based on the abstraction of case elements). In: Proceedings of 72nd National Convention of Information Processing Society of Japan (IPSJ72), pp. 71–72 (2010). (in Japanese)Google Scholar
  7. 7.
    Ishisaka, T., Yamamoto, K.: 2chaeru wo taishō to shita waruguchi hyōgen no chūshutsu (Extraction of abusive expressions from 2channel). In: Proceedings of the Sixteenth Annual Meeting of The Association for Natural Language Processing (NLP2010), pp. 178–181 (2010). (in Japanese)Google Scholar
  8. 8.
    Kilgarriff, A.: Googleology is bad science. Comput. Linguist. 33(1), 147–151 (2007)CrossRefGoogle Scholar
  9. 9.
    Krippendorff, K.: Combinatorial explosion. In: Web Dictionary of Cybernetics and Systems. Principia Cybernetica Web (1986)Google Scholar
  10. 10.
    Matsuba, T., Masui, F., Kawai, A., Isu, N.: Gakkou hikoushiki saito ni okeru yuugai jouhou kenshutsu (Detection of harmful information on informal school websites). In: Proceedings of the 16th Annual Meeting of the Association for Natural Language Processing (NLP2010) (2010). (in Japanese)Google Scholar
  11. 11.
    Matsuba, T., Masui, F., Kawai, A., Isu, N.: Gakkō hi-kōshiki saito ni okeru yūgai jōhō kenshutsu wo mokuteki to shita kyokusei hantei moderu ni kansuru kenkyū (A study on the polarity classification model for the purpose of detecting harmful information on informal school sites). In: Proceedings of the Seventeenth Annual Meeting of the Association for Natural Language Processing (NLP2011), pp. 388–391 (2001). (in Japanese)Google Scholar
  12. 12.
    Ministry of Education, Culture, Sports, Science and Technology (MEXT): ‘Netto-jō no ijime’ ni kansuru taiō manyuaru jirei shū (gakkō, kyōin muke) (“Bullying on the Net” Manual for handling and collection of cases (for schools and teachers)). Published by MEXT (2008). (in Japanese)Google Scholar
  13. 13.
    Nitta, T., Masui, F., Ptaszynski, M., Kimura, Y., Rzepka, R., Araki, K.: Detecting cyberbullying entries on informal school websites based on category relevance maximization. In: Proceedings of the 6th International Joint Conference on Natural Language Processing (IJCNLP 2013), pp. 579–586 (2013)Google Scholar
  14. 14.
    Patchin, J.W., Hinduja, S.: Bullies move beyond the schoolyard: a preliminary look at cyberbullying. Youth Violence Juv. Justice 4(2), 148–169 (2006)CrossRefGoogle Scholar
  15. 15.
    Ptaszynski, M., Dybala, P., Rzepka, R., Araki, K.: Affecting corpora: experiments with automatic affect annotation system - a case study of the 2 channel forum -. In: Proceedings of the Conference of the Pacific Association for Computational Linguistics (PACLING-09), pp. 223–228 (2009)Google Scholar
  16. 16.
    Ptaszynski, M., Dybala, P., Matsuba, T., Masui, F., Rzepka, R., Araki, K., Momouchi, Y.: In the service of online order: tackling cyber-bullying with machine learning and affect analysis. Int. J. Comput. Linguist. Res. 1(3), 135–154 (2010)Google Scholar
  17. 17.
    Ptaszynski, M., Rzepka, R., Araki, K., Momouchi, Y.: Language combinatorics: a sentence pattern extraction architecture based on combinatorial explosion. Int. J. Comput. Linguist. (IJCL) 2(1), 24–36 (2011)Google Scholar
  18. 18.
    Turney, P.D.: Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, pp. 417–424 (2002)Google Scholar
  19. 19.
    Watanabe, H., Sunayama, W.: Denshi keijiban ni okeru yūza no seishitsu no hyōka (User nature evalution on BBS). IEICE Technical report, 105(652), 2006-KBSE, pp. 25–30 (2006). (in Japanese)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Michal Ptaszynski
    • 1
    Email author
  • Fumito Masui
    • 1
  • Yasutomo Kimura
    • 2
  • Rafal Rzepka
    • 3
  • Kenji Araki
    • 3
  1. 1.Department of Computer ScienceKitami Institute of TechnologyKitamiJapan
  2. 2.Department of Information and Management ScienceOtaru University of CommerceOtaruJapan
  3. 3.Graduate School of Information Science and TechnologyHokkaido UniversitySapporoJapan

Personalised recommendations