Offensive Sentence Classification Using Character-Level CNN and Transfer Learning with Fake Sentences

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10635)


There are two difficulties in classifying offensive sentences: One is the modifiability of offensive terms, and the other is the class imbalance which appears in general offensive corpus. Solving these problems, we propose a method of pre-training fake sentences generated as character-level to convolution layers preventing under-fitting from data shortage, and dealing with the data imbalance. We insert the offensive words to half of the randomly generated sentences, and train the convolution neural networks (CNN) with theses sentences and the labels of whether offensive word is included. We use the trained filter of CNN for training new CNN given original data, resulting in the increase of the amount of training data. We get higher F1-score with the proposed method than that without pre-training in three dataset of insult from kaggle, Bullying trace, and formspring.


Text classification Convolution neural networks Character-level model Transfer learning 



This work was supported by Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (R0124-16-0002), Emotional Intelligence Technology to Infer Human Emotion and Carry on Dialogue Accordingly.


  1. 1.
    Chen, Y., Zhou, Y., Zhu, S., Xu, H.: Detecting offensive language in social media to protect adolescent online safety. In: International Conference on Social Computing Privacy, Security, Risk and Trust (PASSAT), pp. 71–80. IEEE (2012)Google Scholar
  2. 2.
    Sood, S.O., Churchill, E.F., Antin, J.: Automatic identification of personal insults on social news sites. J. Assoc. Inf. Sci. Tech. 63, 270–285 (2012)CrossRefGoogle Scholar
  3. 3.
    Xiang, G., Fan, B., Wang, L., Hong, J., Rose, C.: Detecting offensive tweets via topical feature discovery over a large scale twitter corpus. In: 21st International Conference on Information and Knowledge Management, pp. 1980–1984. ACM (2012)Google Scholar
  4. 4.
    Djuric, N., Zhou, J., Morris, R., Grbovic, M.: Hate speech detection with comment embeddings. In: 24th International Conference on WWW, pp. 29–30. ACM (2015)Google Scholar
  5. 5.
    Zhao, R., Zhou, A., Mao, K.: Automatic detection of cyberbullying on social networks based on bullying features. In: 17th International Conference on Distributed Computing and Networking, p. 43. ACM (2016)Google Scholar
  6. 6.
    Nabata, C., Tetreault, J., Thomas, A., Mehdad, Y., Chang, Y.: Abusive language detection in online user content. In: 25th International Conference on WWW, pp. 145–153 (2016)Google Scholar
  7. 7.
    Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems, pp. 649–657 (2015)Google Scholar
  8. 8.
    Detecting Insults in Data Commentary, Kaggle.
  9. 9.
    Xu, J.-M., Jun, K.-S., Zhu, X., Bellmore, A.: Learning from bullying traces in social media. In: Proceedings of Conference of NAACL-HLT, pp. 656–666. ACL (2012)Google Scholar
  10. 10.
    Formspring Labeled for Cyberbullying.

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Computer ScienceYonsei UniversitySeoulRepublic of Korea

Personalised recommendations