Abstract
Making violent threats towards minorities like immigrants or homosexuals is increasingly common on the Internet. We present a method to automatically detect threats of violence using machine learning. A material of 24,840 sentences from YouTube was manually annotated as violent threats or not, and was used to train and test the machine learning model. Detecting threats of violence works quit well with an error of classifying a violent sentence as not violent of about 10% when the error of classifying a non-violent sentence as violent is adjusted to 5%. The best classification performance is achieved by including features that combine specially chosen important words and the distance between those in the sentence.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Fekete, L.: Pedlars of hate: the violent impact of the European far Right. Institute of Race Relations (2013). http://www.irr.org.uk/wp-content/uploads/2012/06/PedlarsofHate.pdf. Accessed 12 Mar 2016
Wilson, R., Hainsworth, P.: Far-right Parties and discourse in Europe: a challenge for our times. European network against racism (2013). http://cms.horus.be/files/99935/MediaArchive/publications/20060_Publication_Far_right_EN_LR.pdf. Accessed 12 Mar 2016
Goodwin, M., Ramalingam, V., Briggs, R.: The new radical right: violent and non-violent movements in Europe. Institute for Strategic Dialogue (2013). http://www.strategicdialogue.org/ISD%20Far%20Right%20Feb2012.pdf. Accessed 12 Mar 2016
Bartlett, J., Birdwell, J., Littler, M.: The rise of populism in Europe can be traced through online behaviour... Demos, (2013). http://www.demos.co.uk/files/Demos_OSIPOP_Book-web_03.pdf?1320601634. Accessed 12 Mar 2016
Strømmen, Ø.: The Dark Net. On Right-Wing Extremism, Counter-Jihadism and Terror in Europe. Cappelen Damm, Oslo (2012)
Sunde, I.M.: Preventing radicalization and violent extremism on the Internet (Norwegian). The Norwegian Police University College 2013:1 (2013)
UnitedNations: International Covenant on Civil and Political Rights (2014). http://www.ohchr.org/en/professionalinterest/pages/ccpr.aspx. Accessed 12 Mar 2016
TheTimesOfIndia: Akbaruddin Owaisi arrested in hate speech case (2014). http://articles.timesofindia.indiatimes.com/2013-01-08/india/36216031_1_nirmal-rural-police-akbaruddin-owaisi-police-stations. Accessed 12 Mar 2016
Skjetne, O.L., Hustadnes, H.: Ubaydullah Hussain is accused of violent threats (norwegian) (2014). http://www.dagbladet.no/2013/11/20/nyheter/ubaydullah_hussain/innenriks/islamisme/trusler/30429704/. Accessed 12 Mar 2016
Euronews: Neo-Nazi and black metal star Varg Vikernes arrested in France (2013). http://www.euronews.com/2013/07/16/neo-nazi-and-black-metal-star-varg-vikernes-arrested-in-france-/. Accessed 12 Mar 2016
Valaker, O., Holte, M.A.: Bergen blogger arrested (norwegian) (2012). http://www.bt.no/nyheter/lokalt/Bergens-blogger-pagrepet-2732162.html. Accessed 12 Mar 2016
Hammer, H.L.: Detecting threats of violence in online discussions using bigrams of important words. In: Intelligence and Security Informatics Conference (JISIC), p. 319 (2014)
Dinakar, K., Reichart, R., Lieberman, H.: Modeling the detection of textual cyberbullying. In: The Social Mobile Web, pp. 11–17 (2011)
Oostdijk, N., Halteren, H.: N-gram-based recognition of threatening tweets. In: Gelbukh, A. (ed.) CICLing 2013. LNCS, vol. 7817, pp. 183–196. Springer, Heidelberg (2013). doi:10.1007/978-3-642-37256-8_16
Oostdijk, N., van Halteren, H.: Shallow parsing for recognizing threats in Dutch tweets. In: Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, pp. 1034–1041. ACM (2013)
Warner, W., Hirschberg, J.: Detecting hate speech on the world wide web. In: Proceedings of the Second Workshop on Language in Social Media, pp. 19–26. Association for Computational Linguistics (2012)
Friedman, J., Hastie, T., Tibshirani, R.: Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw. 33(1), 1–22 (2010)
Genkin, A., Lewis, D.D., Madigan, D.: Large-scale bayesian logistic regression for text categorization. Technometrics 49(14), 291–304 (2007)
R Core Team, R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna (2013)
Fekete, L.: The Muslim conspiracy theory and the Oslo massacre. Technical Report 53(3), pp. 30–47. Institute of Race Relations (2011)
Johnson, R., Wichern, D.: Applied Multivariate Statistical Analysis. Prentece Hall, Upper Saddle River (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Hammer, H.L. (2017). Automatic Detection of Hateful Comments in Online Discussion. In: Maglaras, L., Janicke, H., Jones, K. (eds) Industrial Networks and Intelligent Systems. INISCOM 2016. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 188. Springer, Cham. https://doi.org/10.1007/978-3-319-52569-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-52569-3_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-52568-6
Online ISBN: 978-3-319-52569-3
eBook Packages: Computer ScienceComputer Science (R0)