@InProceedings{karan-najder:2018:ALW2,
  author    = {Karan, Mladen  and  Šnajder, Jan},
  title     = {Cross-Domain Detection of Abusive Language Online},
  booktitle = {Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)},
  month     = {October},
  year      = {2018},
  address   = {Brussels, Belgium},
  publisher = {Association for Computational Linguistics},
  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, specially when used to augment a smaller dataset with a larger one.},
  url       = {http://www.aclweb.org/anthology/W18-5117}
}