@inproceedings{l-etal-2025-itsallgoodman,
    title = "{I}ts{A}ll{G}ood{M}an@{LT}-{EDI}-2025: Fusing {TF}-{IDF} and {M}u{RIL} Embeddings for Detecting Caste and Migration Hate Speech",
    author = "L, Amritha Nandini K  and
      S, Vishal  and
      R, Giri Prasath  and
      Thiyagarajan, Anerud  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-1.15/",
    pages = "90--94",
    ISBN = "978-88-6719-334-9",
    abstract = "Caste and migration hate speech detection is a critical task in the context of increasingly multilingual and diverse online discourse. In this work, we address the problem of identifying hate speech targeting caste and migrant communities across a multilingual social media dataset containing Tamil, Tamil written in English script, and English. We explore and compare different feature representations, including TF-IDF vectors and embeddings from pretrained transformer-based models, to train various machine learning classifiers. Our experiments show that a Soft Voting Classifier that make use of both TF-IDF vectors and MuRIL embeddings performs best, achieving a macro F1 score of 0.802 on the test set. This approach was evaluated as part of the Shared Task on Caste and Migration Hate Speech Detection at LT-EDI@LDK 2025, where it ranked 6th overall."
}