@inproceedings{karan-snajder-2018-cross,
    title = "Cross-Domain Detection of Abusive Language Online",
    author = "Karan, Vanja Mladen  and
      {\v{S}}najder, Jan",
    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/add-emnlp-2024-awards/W18-5117/",
    doi = "10.18653/v1/W18-5117",
    pages = "132--137",
    abstract = "We investigate to what extent the models trained to detect general abusive language generalize between different datasets labeled with different abusive language types. To this end, we compare the cross-domain performance of simple classification models on nine different datasets, finding that the models fail to generalize to out-domain datasets and that having at least some in-domain data is important. We also show that using the frustratingly simple domain adaptation (Daume III, 2007) in most cases improves the results over in-domain training, especially when used to augment a smaller dataset with a larger one."
}