Abstract
Offensive or antagonistic language targeted at individuals and social groups based on their personal characteristics (also known as cyber hate speech or cyberhate) has been frequently posted and widely circulated via the World Wide Web. This can be considered as a key risk factor for individual and societal tension surrounding regional instability. Automated Web-based cyberhate detection is important for observing and understanding community and regional societal tension—especially in online social networks where posts can be rapidly and widely viewed and disseminated. While previous work has involved using lexicons, bags-of-words, or probabilistic language parsing approaches, they often suffer from a similar issue, which is that cyberhate can be subtle and indirect—thus, depending on the occurrence of individual words or phrases, can lead to a significant number of false negatives, providing inaccurate representation of the trends in cyberhate. This problem motivated us to challenge thinking around the representation of subtle language use, such as references to perceived threats from “the other” including immigration or job prosperity in a hateful context. We propose a novel “othering” feature set that utilizes language use around the concept of “othering” and intergroup threat theory to identify these subtleties, and we implement a wide range of classification methods using embedding learning to compute semantic distances between parts of speech considered to be part of an “othering” narrative. To validate our approach, we conducted two sets of experiments. The first involved comparing the results of our novel method with state-of-the-art baseline models from the literature. Our approach outperformed all existing methods. The second tested the best performing models from the first phase on unseen datasets for different types of cyberhate, namely religion, disability, race, and sexual orientation. The results showed F-measure scores for classifying hateful instances obtained through applying our model of 0.81, 0.71, 0.89, and 0.72, respectively, demonstrating the ability of the “othering” narrative to be an important part of model generalization.
- Charu C. Aggarwal. 2015. Similarity and distances. In Data Mining. Springer, 63--91.Google ScholarDigital Library
- Zeynep Akata, Florent Perronnin, Zaid Harchaoui, and Cordelia Schmid. 2016. Label-embedding for image classification. IEEE Trans. Pattern Anal. Mach. Intell. 38, 7 (2016), 1425--1438.Google ScholarCross Ref
- Muhammad Zubair Asghar, Aurangzeb Khan, Shakeel Ahmad, Maria Qasim, and Imran Ali Khan. 2017. Lexicon-enhanced sentiment analysis framework using rule-based classification scheme. PloS One 12, 2 (2017), e0171649.Google ScholarCross Ref
- Pinkesh Badjatiya, Shashank Gupta, Manish Gupta, and Vasudeva Varma. 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, 759--760. Google ScholarDigital Library
- Mario Guajardo-Céspedes 8 Margaret Mitchell Ben Packer, Yoni Halpern. 2018. Text Embedding Models Contain Bias. Here’s Why That Matters. Retrieved from https://developers.googleblog.com/2018/04/text-embedding-models-contain-bias.html.Google Scholar
- Darina Benikova, Michael Wojatzki, and Torsten Zesch. 2017. What does this imply? Examining the impact of implicitness on the perception of hate speech. In International Conference of the German Society for Computational Linguistics and Language Technology. Springer, 171--179.Google Scholar
- Adam Bermingham and Alan F. Smeaton. 2010. Classifying sentiment in microblogs: Is brevity an advantage? In Proceedings of the 19th ACM International Conference on Information and Knowledge Management. ACM, 1833--1836. Google ScholarDigital Library
- Leo Breiman. 2001. Random forests. Machine Learning 45, 1 (2001), 5--32. Google ScholarDigital Library
- Peter Burnap and Matthew Leighton Williams. 2014. Hate speech, machine classification and statistical modelling of information flows on Twitter: Interpretation and communication for policy decision making. In Internet, Policy 8 Politics, Oxford, UK.Google Scholar
- Pete Burnap and Matthew L. Williams. 2015. Cyber hate speech on Twitter: An application of machine classification and statistical modeling for policy and decision making. Policy 8 Internet 7, 2 (2015), 223--242.Google Scholar
- Pete Burnap and Matthew L. Williams. 2016. Us and them: Identifying cyber hate on Twitter across multiple protected characteristics. EPJ Data Sci. 5, 1 (2016), 11.Google ScholarCross Ref
- Ying Chen, Yilu Zhou, Sencun Zhu, and Heng Xu. 2012. Detecting offensive language in social media to protect adolescent online safety. In 2012 International Conference on Privacy, Security, Risk and Trust (PASSAT) and 2012 International Confernece on Social Computing (SocialCom). IEEE, 71--80. Google ScholarDigital Library
- Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014).Google Scholar
- Isobelle Clarke and Jack Grieve. 2017. Dimensions of abusive language on Twitter. In Proceedings of the 1st Workshop on Abusive Language Online. 1--10.Google ScholarCross Ref
- Stephen M. Croucher. 2013. Integrated threat theory and acceptance of immigrant assimilation: An analysis of Muslim immigration in Western Europe. Commun. Monogr. 80, 1 (2013), 46--62. arXiv:https://doi.org/10.1080/03637751.2012.739704Google ScholarCross Ref
- Thomas Davidson, Dana Warmsley, Michael Macy, and Ingmar Weber. 2017. Automated hate speech detection and the problem of offensive language. arXiv preprint arXiv:1703.04009 (2017).Google Scholar
- Marie-Catherine De Marneffe and Christopher D. Manning. 2008. Stanford Typed Dependencies Manual. Technical report, Stanford University.Google Scholar
- Fabio Del Vigna12, Andrea Cimino23, Felice Dell’Orletta, Marinella Petrocchi, and Maurizio Tesconi. 2017. Hate me, hate me not: Hate speech detection on Facebook. (2017).Google Scholar
- Nemanja Djuric, Jing Zhou, Robin Morris, Mihajlo Grbovic, Vladan Radosavljevic, and Narayan Bhamidipati. 2015. Hate speech detection with comment embeddings. In Proceedings of the 24th International Conference on World Wide Web. ACM, 29--30. Google ScholarDigital Library
- Iginio Gagliardone, Danit Gal, Thiago Alves, and Gabriela Martinez. 2015. Countering Online Hate Speech. UNESCO Publishing.Google Scholar
- Björn Gambäck and Utpal Kumar Sikdar. 2017. Using convolutional neural networks to classify hate-speech. In Proceedings of the 1st Workshop on Abusive Language Online. 85--90.Google ScholarCross Ref
- Lei Gao, Alexis Kuppersmith, and Ruihong Huang. 2017. Recognizing explicit and implicit hate speech using a weakly supervised two-path bootstrapping approach. arXiv preprint arXiv:1710.07394Google Scholar
- Sahar Ghannay, Yannick Esteve, and Nathalie Camelin. 2015. Word embeddings combination and neural networks for robustness in ASR error detection. In 23rd European Signal Processing Conference (EUSIPCO’15). IEEE, 1671--1675.Google ScholarCross Ref
- Manoochehr Ghiassi, James Skinner, and David Zimbra. 2013. Twitter brand sentiment analysis: A hybrid system using n-gram analysis and dynamic artificial neural network. Expert Syst. Appl. 40, 16 (2013), 6266--6282. Google ScholarDigital Library
- Njagi Dennis Gitari, Zhang Zuping, Hanyurwimfura Damien, and Jun Long. 2015. A lexicon-based approach for hate speech detection. Int. J. Multimedia Ubiquitous Eng. 10, 4 (2015), 215--230.Google ScholarCross Ref
- Edel Greevy and Alan F. Smeaton. 2004. Classifying racist texts using a support vector machine. In Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 468--469. Google ScholarDigital Library
- Geoffrey E. Hinton, Simon Osindero, and Yee-Whye Teh. 2006. A fast learning algorithm for deep belief nets. Neural Comput. 18, 7 (2006), 1527--1554. Google ScholarDigital Library
- Minqing Hu and Bing Liu. 2004. Mining and summarizing customer reviews. In Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 168--177. Google ScholarDigital Library
- Jin Huang and Charles X. Ling. 2005. Using AUC and accuracy in evaluating learning algorithms. IEEE Trans. Knowl. Data Eng. 17, 3 (2005), 299--310. Google ScholarDigital Library
- Mohit Iyyer, Varun Manjunatha, Jordan Boyd-Graber, and Hal Daumé III. 2015. Deep unordered composition rivals syntactic methods for text classification. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Vol. 1. 1681--1691.Google ScholarCross Ref
- Akshita Jha and Radhika Mamidi. 2017. When does a compliment become sexist? Analysis and classification of ambivalent sexism using Twitter data. In Proceedings of the 2nd Workshop on NLP and Computational Social Science. 7--16.Google ScholarCross Ref
- Christopher S. Josey. 2010. Hate speech and identity: An analysis of neo racism and the indexing of identity. Discourse 8 Society 21, 1 (2010), 27--39.Google Scholar
- Eunice Kim, Yongjun Sung, and Hamsu Kang. 2014. Brand followers’ retweeting behavior on Twitter: How brand relationships influence brand electronic word-of-mouth. Comput. Hum. Behav. 37 (2014), 18--25. Google ScholarDigital Library
- Yoon Kim, Yi-I Chiu, Kentaro Hanaki, Darshan Hegde, and Slav Petrov. 2014. Temporal analysis of language through neural language models. arXiv preprint arXiv:1405.3515.Google Scholar
- Sebastian Köffer, Dennis M. Riehle, Steffen Höhenberger, and Jörg Becker. 2018. Discussing the value of automatic hate speech detection in online debates. Multikonferenz Wirtschaftsinformatik (MKWI 2018): Data Driven X-Turning Data in Value, Leuphana, Germany (2018).Google Scholar
- Alexandros Komninos and Suresh Manandhar. 2016. Dependency based embeddings for sentence classification tasks. In Proceedings of NAACL-HLT. 1490--1500.Google ScholarCross Ref
- Quoc V. Le and Tomas Mikolov. 2014. Distributed representations of sentences and documents. In ICML, Vol. 14. 1188--1196. Google ScholarDigital Library
- Laura Leets. 2001. Responses to Internet hate sites: Is speech too free in cyberspace? Commun. Law Policy 6, 2 (2001), 287--317.Google ScholarCross Ref
- Omer Levy and Yoav Goldberg. 2014. Dependency-based word embeddings. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 302--308.Google ScholarCross Ref
- Xu-Ying Liu, Jianxin Wu, and Zhi-Hua Zhou. 2009. Exploratory undersampling for class-imbalance learning. IEEE Trans. Syst. Man Cybern. Part B Cybern. 39, 2 (2009), 539--550. Google ScholarDigital Library
- Shervin Malmasi and Marcos Zampieri. 2017. Detecting hate speech in social media. arXiv preprint arXiv:1712.06427Google Scholar
- Priscilla Marie Meddaugh and Jack Kay. 2009. Hate speech or “reasonable racism?” The other in Stormfront. J. Mass Media Ethics 24, 4 (2009), 251--268.Google ScholarCross Ref
- Yashar Mehdad and Joel Tetreault. 2016. Do characters abuse more than words? In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 299--303.Google ScholarCross Ref
- Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013).Google Scholar
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S. Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems. 3111--3119. Google ScholarDigital Library
- Kevin Munger. 2017. Tweetment effects on the tweeted: Experimentally reducing racist harassment. Political Behav. 39, 3 (2017), 629--649.Google ScholarCross Ref
- Chikashi Nobata, Joel Tetreault, Achint Thomas, Yashar Mehdad, and Yi Chang. 2016. Abusive language detection in online user content. In Proceedings of the 25th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 145--153. Google ScholarDigital Library
- Alexander Pak and Patrick Paroubek. 2010. Twitter as a corpus for sentiment analysis and opinion mining. In LREc, Vol. 10. 1320--1326.Google Scholar
- Aasish Pappu and Amanda Stent. 2015. Location-Based Recommendations Using Nearest Neighbors in a Locality Sensitive Hashing (LSH) Index. US Patent App. 14, 948,213 (2015).Google Scholar
- Barbara Perry and Patrik Olsson. 2009. Cyberhate: The globalization of hate. Inf. Commun. Technol. Law 18, 2 (2009), 185--199.Google ScholarCross Ref
- Georgios K. Pitsilis, Heri Ramampiaro, and Helge Langseth. 2018. Effective hate-speech detection in Twitter data using recurrent neural networks. Appl. Intell. 48, 12 (2018), 4730--4742. Google ScholarDigital Library
- Haji Mohammad Saleem, Kelly P. Dillon, Susan Benesch, and Derek sRuths. 2017. A web of hate: Tackling hateful speech in online social spaces. arXiv preprint arXiv:1709.10159 (2017).Google Scholar
- Scharolta Katharina Sienčnik. 2015. Adapting word2vec to named entity recognition. In Proceedings of the 20th Nordic Conference of Computational Linguistics, NODALIDA 2015, May 11--13, 2015, Vilnius, Lithuania. Linköping University Electronic Press, 239--243.Google Scholar
- Leandro Araújo Silva, Mainack Mondal, Denzil Correa, Fabrício Benevenuto, and Ingmar Weber. 2016. Analyzing the targets of hate in online social media. In ICWSM. 687--690.Google Scholar
- Walter G. Stephan and Cookie White Stephan. 2017. Intergroup threat theory. The International Encyclopedia of Intercultural Communication (2017), 1--12.Google Scholar
- Walter G. Stephan, Cookie White Stephan, and William B. Gudykunst. 1999. Anxiety in intergroup relations: A comparison of anxiety/uncertainty management theory and integrated threat theory. Int. J. Intercultural Relations 23, 4 (1999), 613--628.Google ScholarCross Ref
- Luke Kien-Weng Tan, Jin-Cheon Na, Yin-Leng Theng, and Kuiyu Chang. 2012. Phrase-level sentiment polarity classification using rule-based typed dependencies and additional complex phrases consideration. J. Comput. Sci. Technol. 27, 3 (2012), 650--666.Google ScholarCross Ref
- Mike Thelwall, Kevan Buckley, Georgios Paltoglou, Di Cai, and Arvid Kappas. 2010. Sentiment strength detection in short informal text. J. Am. Soc. Inf. Sci. Technol. 61, 12 (2010), 2544--2558. Google ScholarCross Ref
- Teun A. Van Dijk. 1993. Elite Discourse and Racism. Vol. 6. Sage.Google Scholar
- Zeerak Waseem, Thomas Davidson, Dana Warmsley, and Ingmar Weber. 2017. Understanding abuse: A typology of abusive language detection subtasks. arXiv preprint arXiv:1705.09899 (2017).Google Scholar
- Zeerak Waseem and Dirk Hovy. 2016. Hateful symbols or hateful people? Predictive features for hate speech detection on Twitter. In Proceedings of NAACL-HLT. 88--93.Google ScholarCross Ref
- Hajime Watanabe, Mondher Bouazizi, and Tomoaki Ohtsuki. 2018. Hate speech on Twitter: A pragmatic approach to collect hateful and offensive expressions and perform hate speech detection. IEEE Access 6, 2018 (2018), 13825--13835.Google ScholarCross Ref
- Casey Whitelaw, Navendu Garg, and Shlomo Argamon. 2005. Using appraisal groups for sentiment analysis. In Proceedings of the 14th ACM International Conference on Information and Knowledge Management. ACM, 625--631. Google ScholarDigital Library
- Matthew L. Williams and Pete Burnap. 2016. Cyberhate on social media in the aftermath of Woolwich: A case study in computational criminology and big data. Br. J. Criminology 56, 2 (2016), 211--238.Google ScholarCross Ref
- Matthew L. Williams and Jasmin Tregidga. 2014. Hate crime victimization in Wales: Psychological and physical impacts across seven hate crime victim types. Br. J. Criminology 54, 5 (2014), 946--967.Google ScholarCross Ref
- Theresa Wilson, Janyce Wiebe, and Paul Hoffmann. 2005. Recognizing contextual polarity in phrase-level sentiment analysis. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 347--354. Google ScholarDigital Library
- Ruth Wodak. 2009. Discursive Construction of National Identity. Edinburgh University Press.Google Scholar
- Ruth Wodak and Norman Fairclough. 1997. Critical discourse analysis. Discourse as Social Interaction, T. A. van Dijk (Ed.). Sage, 258--284.Google Scholar
- Ruth Wodak and Martin Reisigl. 1999. Discourse and racism: European perspectives. Annual Review of Anthropology 28, 1 (1999), 175--199.Google ScholarCross Ref
- Ellery Wulczyn, Nithum Thain, and Lucas Dixon. 2017. Ex machina: Personal attacks seen at scale. In Proceedings of the 26th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 1391--1399. Google ScholarDigital Library
- Ziqi Zhang and Lei Luo. 2018. Hate speech detection: A solved problem? The challenging case of long tail on Twitter. arXiv preprint arXiv:1803.03662 (2018).Google Scholar
- Ziqi Zhang, David Robinson, and Jonathan Tepper. 2018. Detecting hate speech on Twitter using a convolution-GRU based deep neural network. In European Semantic Web Conference. Springer, 745--760.Google ScholarCross Ref
- Ziqi Zhang, David Robinson, and Jonathan Tepper. 2018b. Detecting hate speech on Twitter using a convolution-GRU based deep neural network. In European Semantic Web Conference. Heraklion, Crete.Google ScholarCross Ref
- Yinggong Zhao, Shujian Huang, Xinyu Dai, Jianbing Zhang, and Jiajun Chen. 2014. Learning word embeddings from dependency relations. In International Conference on Asian Language Processing (IALP’14). IEEE, 123--127.Google ScholarCross Ref
Index Terms
- “The Enemy Among Us”: Detecting Cyber Hate Speech with Threats-based Othering Language Embeddings
Recommendations
A Measurement Study of Hate Speech in Social Media
HT '17: Proceedings of the 28th ACM Conference on Hypertext and Social MediaSocial media platforms provide an inexpensive communication medium that allows anyone to quickly reach millions of users. Consequently, in these platforms anyone can publish content and anyone interested in the content can obtain it, representing a ...
The Dynamics of (Not) Unfollowing Misinformation Spreaders
WWW '24: Proceedings of the ACM on Web Conference 2024Many studies explore how people "come into" misinformation exposure. But much less is known about how people "come out of" misinformation exposure.Do people organically sever ties to misinformation spreaders? And what predicts doing so? Over six months, ...
Information resonance on Twitter: watching Iran
SOMA '10: Proceedings of the First Workshop on Social Media AnalyticsTwitter has undoubtedly caught the attention of both the general public, and academia as a microblogging service worthy of study and attention. Twitter has several features that sets it apart from other social media/networking sites, including its 140 ...
Comments