ABARUAH at SemEval-2019 Task 5 : Bi-directional LSTM for Hate Speech Detection

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 371–376 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 371 ABARUAH at SemEval-2019 Task 5 : Bi-directional LSTM for Hate Speech Detection Arup Baruah Dept. of Comp. Sc. & Engg. IIIT Guwahati, India arup.baruah@gmail.com Ferdous Ahmed Barbhuiya Dept. of Comp. Sc. & Engg. IIIT Guwahati, India ferdous@iiitg.ac.in Kuntal Dey IBM Research India New Delhi kuntadey@in.ibm.com Abstract In this paper, we present the results obtained using bi-directional long short-term memory (BiLSTM) with and without attention and Lo- gistic Regression (LR) models for SemEval- 2019 Task 5 titled ”HatEval: Multilingual De- tection of Hate Speech Against Immigrants and Women in Twitter”. This paper presents the results obtained for Subtask A for English language. The results of the BiLSTM and LR models are compared for two different types of preprocessing. One with no stemming per- formed and no stopwords removed. The other with stemming performed and stopwords re- moved. The BiLSTM model without attention performed the best for the first test, while the LR model with character n-grams performed the best for the second test. The BiLSTM model obtained an F1 score of 0.51 on the test set and obtained an official ranking of 8/71. 1 Introduction Davidson et al. (2017) has defined hate speech as “language that is used to express hatred to- wards a targeted group or is intended to be deroga- tory, to humiliate, or to insult the members of the group.” Gamb¨ack and Sikdar (2017), Badjatiya et al. (2017), Waseem (2016) and Waseem et al. (2017) have used the term hate speech to indicate tweets having racist or sexist comments. Social media is becoming a convenient medium to spread hate speech. Hate speech spread through social media has fueled riots in Myanmar 1, Sri Lanka 2, Charlottesville (USA) 3, and many other parts of the world. Thus, it is becoming increasingly im- portant to detect and remove hate messages from 1https://www.nytimes.com/2018/10/15/technology/ myanmar-facebook-genocide.html 2https://qz.com/1223787/sri-lanka-shut-down-facebook- whatsapp-and-instagram-to-stop-anti-muslim-violence/ 3https://psmag.com/social-justice/how-social-media- helped-organize-and-radicalize-americas-newest-white- supremacists the web. It is not possible to manually moder- ate the vast amount of text exchanged on the web. Developing automated systems to recognize hate speech is becoming crucially important. However, detecting hate speech in a text is more than just checking for the presence of hate words. Lexicon based approaches have not been very effective in hate speech detection (Nobata et al., 2016). As part of the 13th workshop on semantic eval- uation (SemEval-2019), shared task 5 defines two subtasks with regard to detection of hate speech against immigrants and women in Twitter (Basile et al., 2019). This task was conducted for tweets in English and Spanish language. In Subtask A, it is required to determine if a tweet, with a given tar- get, is hateful or not. In Subtask B, it is required to determine if a given hateful tweet is aggressive or not and whether it targets an individual or a group. 2 Related Work Nobata et al. (2016) studied the performance of different features …

Content truncated to 500 words