@inproceedings{bichi-shekhawat-2026-vgu,
    title = "{VGU}-{M}.{T}ech-{AI} at {S}em{E}val-2026: Multilingual Multi-Label Classification of Online Polarization Types via Weighted Transformer Fine-Tuning and Adaptive Per-Label Threshold Optimization",
    author = "Bichi, Abdulkadir  and
      Shekhawat, Jyoti",
    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-1.183/",
    pages = "1416--1420",
    ISBN = "979-8-89176-414-9",
    abstract = "Abstract This research paper proposed a multilingual multi-label classification of online polarization types via weighted transformer fine-tuning and adaptive per-label threshold optimization (MMCOPT). Our task is to classify social media posts according to a given set of five labels. A post could be deemed to be politically, racially, religiously, or gender/sexually polarizing, or fall into the category of other. We incorporate a distilbert-base-multilingualcased model and attach a two-layer MLP head. We also use a class-imbalance-weighted binary cross-entropy loss and optimize thresholds for each class to improve the validation micro-F1 score. Our training set is drawn from the POLAR benchmark, the first large multilingual polarization dataset that includes posts from seven languages and multiple social media platforms. MMCOPT{'}s best internal validation micro-F1 score is 0.7855, and its macro-F1 score is 0.7749. Our model (team username: asbichi362) is ranked on the official Codabench leaderboard and shows competitive results across 22 language tracks of the research project multilingual polarization type classification, with its best results in Hindi (0.7429) and Urdu (0.7073)."
}