@inproceedings{wiegand-etal-2019-detection,
    title = "{D}etection of {A}busive {L}anguage: the {P}roblem of {B}iased {D}atasets",
    author = "Wiegand, Michael  and
      Ruppenhofer, Josef  and
      Kleinbauer, Thomas",
    editor = "Burstein, Jill  and
      Doran, Christy  and
      Solorio, Thamar",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/N19-1060/",
    doi = "10.18653/v1/N19-1060",
    pages = "602--608",
    abstract = "We discuss the impact of data bias on abusive language detection. We show that classification scores on popular datasets reported in previous work are much lower under realistic settings in which this bias is reduced. Such biases are most notably observed on datasets that are created by focused sampling instead of random sampling. Datasets with a higher proportion of implicit abuse are more affected than datasets with a lower proportion."
}