@inproceedings{gajewska-2023-eevvgg,
    title = "eevvgg at {S}em{E}val-2023 Task 11: Offensive Language Classification with Rater-based Information",
    author = "Gajewska, Ewelina",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Da San Martino, Giovanni  and
      Tayyar Madabushi, Harish  and
      Kumar, Ritesh  and
      Sartori, Elisa},
    booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.semeval-1.24/",
    doi = "10.18653/v1/2023.semeval-1.24",
    pages = "171--176",
    abstract = "A standard majority-based approach to text classification is challenged with an individualised approach in the Semeval-2023 Task 11. Here, disagreements are treated as a useful source of information that could be utilised in the training pipeline. The team proposal makes use of partially disaggregated data and additional information about annotators provided by the organisers to train a BERT-based model for offensive text classification. The approach extends previous studies examining the impact of using raters' demographic features on classification performance (Hovy, 2015) or training machine learning models on disaggregated data (Davani et al., 2022). The proposed approach was ranked 11 across all 4 datasets, scoring best for cases with a large pool of annotators (6th place in the MD-Agreement dataset) utilising features based on raters' annotation behaviour."
}