@inproceedings{973ac1160d224a5996a01b3df179120e,
title = "Arabic Offensive Language Classification on Twitter",
abstract = "Social media users often employ offensive language in their communication. Detecting offensive language on Twitter has many applications ranging from detecting/predicting conflict to measuring polarization. In this paper, we focus on building effective offensive tweet detection. We show that we can rapidly build a training set using a seed list of offensive words. Given the automatically created dataset, we trained a character n-gram based deep learning classifier that can effectively classify tweets with F1 score of 90%. We also show that we can expand our offensive word list by contrasting offensive and non-offensive tweets.",
keywords = "Obscenities, Offensive language, Text classification",
author = "Hamdy Mubarak and Kareem Darwish",
note = "Publisher Copyright: {\textcopyright} 2019, Springer Nature Switzerland AG.; 11th International Conference on Social Informatics, SocInfo 2019 ; Conference date: 18-11-2019 Through 21-11-2019",
year = "2019",
doi = "10.1007/978-3-030-34971-4_18",
language = "English",
isbn = "9783030349707",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer",
pages = "269--276",
editor = "Ingmar Weber and Darwish, {Kareem M.} and Claudia Wagner and Claudia Wagner and Fabian Fl{\"o}ck and Emilio Zagheni and Samin Aref and Laura Nelson",
booktitle = "Social Informatics - 11th International Conference, SocInfo 2019, Proceedings",
address = "Germany",
}