@inproceedings{dey-etal-2026-cuet-data,
    title = "{C}uet{\_}{D}ata{\_}{W}izards at {\#}{SMM}4{H}-{H}ea{RD} 2026: Multilingual {ADE} Detection and Influenza Vaccine Effectiveness Estimation from Social Media",
    author = "Dey, Abir  and
      Faiaz, Mohammed Omar  and
      Khan, Muhammad Ibrahim",
    editor = "Lopez-Garcia, Guillermo  and
      Gonzalez-Hernandez, Graciela",
    booktitle = "Proceedings of the 11th Social Media Mining for Health Research and Applications ({SMM}4{H}-{H}ea{RD} 2026) Workshop and Shared Tasks",
    month = jul,
    year = "2026",
    address = "San Diego, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.smm4h-1.36/",
    pages = "225--229",
    ISBN = "979-8-89176-432-3",
    abstract = "We present our systems for Task 1 and Task 3 of the {\#}SMM4H-HeaRD 2026 shared tasks. Task 1 focuses on binary classification of adverse drug event (ADE) mentions across seven languages, including a zero-shot Persian setting without labeled training data. We fine-tune XLM-RoBERTa-large using weighted cross-entropy loss and augment low-resource settings with additional CADEC data and machine translation-based Persian augmentation. Our system achieves a macro F1 score of 0.582, outperforming the shared task average of 0.547. Task 3 addresses influenza vaccine effectiveness estimation through classification of vaccination status and flu-test results from X posts. We fine-tune twitter-roberta-large, achieving micro F1 scores of 0.845 for vaccination status and 0.883 for flu-test classification on the official test set. Post-evaluation experiments with focal loss, test-time augmentation, and head-tail truncation further improve performance. These results highlight the effectiveness of robust transformer adaptation for health-related social media classification."
}