@inproceedings{ed2c0096594344159f4a7b19494c394d,
title = "Abusive language detection on Arabic social media",
abstract = "In this paper, we present our work on detecting abusive language on Arabic social media. We extract a list of obscene words and hashtags using common patterns used in offensive and rude communications. We also classify Twitter users according to whether they use any of these words or not in their tweets. We expand the list of obscene words using this classification, and we report results on a newly created dataset of classified Arabic tweets (obscene, offensive, and clean). We make this dataset freely available for research, in addition to the list of obscene words and hashtags. We are also publicly releasing a large corpus of classified user comments that were deleted from a popular Arabic news site due to violations the site's rules and guidelines.",
author = "Hamdy Mubarak and Kareem Darwish and Walid Magdy",
note = "Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics; 1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop ; Conference date: 04-08-2017",
year = "2017",
language = "English",
series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics (ACL)",
pages = "52--56",
editor = "Zeerak Waseem and Chung, {Wendy Hui Kyong} and Dirk Hovy and Joel Tetreault",
booktitle = "1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop",
address = "United States",
}