@inproceedings{s-etal-2025-ns,
    title = "{NS}@{LT}-{EDI}-2025 {C}aste{M}igration based hate speech Detection",
    author = "S, Nishanth  and
      Rengarajan, Shruthi  and
      S, Sachin Kumar",
    editor = "Gkirtzou, Katerina  and
      {\v{Z}}itnik, Slavko  and
      Gracia, Jorge  and
      Gromann, Dagmar  and
      di Buono, Maria Pia  and
      Monti, Johanna  and
      Ionov, Maxim",
    booktitle = "Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion",
    month = sep,
    year = "2025",
    address = "Naples, Italy",
    publisher = "Unior Press",
    url = "https://preview.aclanthology.org/corrections-2025-10/2025.ltedi-1.13/",
    pages = "80--83",
    ISBN = "978-88-6719-334-9",
    abstract = "Hate speech directed at caste and migrant communities is a widespread problem on social media, frequently taking the form of insults specific to a given region, coded language, and disparaging slurs. This type of abuse seriously jeopardizes both individual well-being and social harmony in addition to perpetuating discrimination. In order to promote safer and more inclusive digital environments, it is imperative that this challenge be addressed. However, linguistic subtleties, code-mixing, and the lack of extensive annotated datasets make it difficult to detect such hate speech in Indian languages like Tamil. We suggest a supervised machine learning system that uses FastText embeddings specifically designed for Tamil-language content and Whisper-based speech recognition to address these issues. This strategy aims to precisely identify hate speech connected to caste and migration, supporting the larger endeavor to reduce online abuse in low resource languages like Tamil."
}