@inproceedings{yoder-etal-2023-weakly,
    title = "A Weakly Supervised Classifier and Dataset of White Supremacist Language",
    author = "Yoder, Michael  and
      Diab, Ahmad  and
      Brown, David  and
      Carley, Kathleen",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2023.acl-short.17/",
    doi = "10.18653/v1/2023.acl-short.17",
    pages = "172--185",
    abstract = "We present a dataset and classifier for detecting the language of white supremacist extremism, a growing issue in online hate speech. Our weakly supervised classifier is trained on large datasets of text from explicitly white supremacist domains paired with neutral and anti-racist data from similar domains. We demonstrate that this approach improves generalization performance to new domains. Incorporating anti-racist texts as counterexamples to white supremacist language mitigates bias."
}