@inproceedings{engelmann-etal-2024-dataset,
    title = "A Dataset for the Detection of Dehumanizing Language",
    author = "Engelmann, Paul  and
      Trolle, Peter  and
      Hardmeier, Christian",
    editor = {Chakravarthi, Bharathi Raja  and
      B, Bharathi  and
      Buitelaar, Paul  and
      Durairaj, Thenmozhi  and
      Kov{\'a}cs, Gy{\"o}rgy  and
      Garc{\'i}a Cumbreras, Miguel {\'A}ngel},
    booktitle = "Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion",
    month = mar,
    year = "2024",
    address = "St. Julian's, Malta",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2024.ltedi-1.2/",
    pages = "14--20",
    abstract = "Dehumanization is a mental process that enables the exclusion and ill treatment of a group of people. In this paper, we present two data sets of dehumanizing text, a large, automatically collected corpus and a smaller, manually annotated data set. Both data sets include a combination of political discourse and dialogue from movie subtitles. Our methods give us a broad and varied amount of dehumanization data to work with, enabling further exploratory analysis as well as automatic classification of dehumanization patterns. Both data sets will be publicly released."
}