@inproceedings{takahashi-etal-2026-ozemi,
    title = "{OZ}emi at {S}em{E}val-2026 Task 9: A Cross-Lingual Approach to Online Text Polarization Classification Using Multilingual Models and Adaptive Loss Formulation",
    author = "Takahashi, Hidetsune  and
      Nusi Tee, Eleale  and
      Yu, Aika  and
      Furukawa, Ruri  and
      Kim, Sooeun  and
      Niinomi, Shuta  and
      Zhang, Dingyu  and
      Ohman, Emily",
    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-1.27/",
    pages = "182--192",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper presents the OZemi team{'}s submission to SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization.We propose a unified multilingual approach that addresses multiple languages and subtasks efficiently. Our system combines multilingual models with data-level techniques and a class-weighted cross-entropy loss to mitigate data imbalance across languages, subtasks, and categories. Results show consistent performance across languages, achieving macro F1 scores above 70{\%} in most languages for Subtask 1 achieving our highest rank in subtask 1 for Persian (1 out of 44). These results suggest that the proposed framework provides a flexible foundation for multilingual and multi-task polarization analysis."
}