Hate Speech Detection

Introduction

Hate speech can be defined as speech that attacks a person or group on the basis of attributes such as race, religion, ethnic origin, sexual orientation, disability or gender. Hateful speech is widespread in the public debate, including on online platforms, social media and forums.

Online hate speech has debilitating consequences on individual victims’ well-being by imposing psychological harm, damaging self-worth and inducing fear. The duration of the exposure maintained by the online availability of the content is associated with greater damage on victims and greater empowerment of perpetrators compared to offline hate speech. Therefore, the sooner the content is down, the better the chances to mitigate the negative effects of hate speech on victims’ well-being.

Our contributions

  1. In order to fight online hate speech, we created Hatebusters, which is a platform that aims to reduce online hate speech on YouTube through active participation. In Hatebusters, we believe that online communities should be inclusive, respectful and diverse. Therefore, we are commited to trying to reduce hate speech comments as much as possible. Register to Hatebusters and in order to fight hate speech.
  2. We collected a dataset so that we could build a machine learning model capable of classifying YouTube comments in two categories, comments with/without HateSpeech. This dataset can be accessible by clicking here:  Link to download dataset and Link to download description. For the purpose of using this dataset, please cite the publication below.

Awards

Thanks to this award, we aim to publish a new multi-labeled dataset on hate speech in the near future.

Publications

A. Anagnostou, I. Mollas, G. Tsoumakas (2018) Hatebusters: A Web Application for Actively Reporting YouTube Hate Speech, Proceedings of the 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence (IJCAI ECAI 2018), Stockholm, Sweden, July 13-19, 2018