@inproceedings{wazir-etal-2026-upr,
    title = "{UPR} at {S}em{E}val-2026 Task 9: Polarization Detection in {U}rdu with Language-Specific Transformer and Data Augmentation",
    author = "Wazir, Alishba  and
      Asad Khan, Muhammad  and
      Rashid, Junaid  and
      Hayat, Shamaila  and
      Kanwal, Samira",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.332/",
    pages = "2635--2641",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper addresses polarization detection in Urdu, a low-resource language characterized by complex morphology and insufficient annotated data. We formulate the task as a binary classification problem of social media posts into polarized and non-polarized categories. Our approach is based on Urdu-BERT, a language-specific transformer model combined with language-specific preprocessing, duplicate removal, and data augmentation to mitigate class imbalance and improve generalization. Experimental results show that the fine-tuned Urdu-BERT outperforms TF-IDF-based lexical machine learning baselines and achieves strong performance relative to multilingual transformer baselines. The findings indicate that language-specific pretrained transformers, when combined with appropriate preprocessing and augmentation strategies, provide an effective and generalizable framework for low-resource Urdu polarization detection."
}