@inproceedings{junior-etal-2025-privacy,
    title = "Privacy-Preserving Federated Learning for Hate Speech Detection",
    author = {de Souza Bueno J{\'u}nior, Ivo  and
      Ye, Haotian  and
      Wisiorek, Axel  and
      Sch{\"u}tze, Hinrich},
    editor = "Ebrahimi, Abteen  and
      Haider, Samar  and
      Liu, Emmy  and
      Haider, Sammar  and
      Leonor Pacheco, Maria  and
      Wein, Shira",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
    month = apr,
    year = "2025",
    address = "Albuquerque, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-srw.13/",
    pages = "129--141",
    ISBN = "979-8-89176-192-6",
    abstract = "This paper presents a federated learning system with differential privacy for hate speech detection, tailored to low-resource languages. By fine-tuning pre-trained language models, ALBERT emerged as the most effective option for balancing performance and privacy. Experiments demonstrated that federated learning with differential privacy performs adequately in low-resource settings, though datasets with fewer than 20 sentences per client struggled due to excessive noise. Balanced datasets and augmenting hateful data with non-hateful examples proved critical for improving model utility. These findings offer a scalable and privacy-conscious framework for integrating hate speech detection into social media platforms and browsers, safeguarding user privacy while addressing online harm."
}