@inproceedings{castelle-2018-linguistic,
    title = "The Linguistic Ideologies of Deep Abusive Language Classification",
    author = "Castelle, Michael",
    editor = "Fi{\v{s}}er, Darja  and
      Huang, Ruihong  and
      Prabhakaran, Vinodkumar  and
      Voigt, Rob  and
      Waseem, Zeerak  and
      Wernimont, Jacqueline",
    booktitle = "Proceedings of the 2nd Workshop on Abusive Language Online ({ALW}2)",
    month = oct,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W18-5120/",
    doi = "10.18653/v1/W18-5120",
    pages = "160--170",
    abstract = "This paper brings together theories from sociolinguistics and linguistic anthropology to critically evaluate the so-called {\textquotedblleft}language ideologies{\textquotedblright} {---} the set of beliefs and ways of speaking about language{---}in the practices of abusive language classification in modern machine learning-based NLP. This argument is made at both a conceptual and empirical level, as we review approaches to abusive language from different fields, and use two neural network methods to analyze three datasets developed for abusive language classification tasks (drawn from Wikipedia, Facebook, and StackOverflow). By evaluating and comparing these results, we argue for the importance of incorporating theories of pragmatics and metapragmatics into both the design of classification tasks as well as in ML architectures."
}