@inproceedings{ben-arbia-etal-2026-comparative,
    title = "Comparative Study of Machine Learning and Transformer-Based Approaches for {A}rabic Politeness Detection at {A}dab{E}val 2026",
    author = "Ben Arbia, Mariem  and
      Ben Amor, Ghada  and
      Trigui, Omar",
    editor = "Al-Khalifa, Hend  and
      El-Haj, Mo  and
      Ezzini, Saad",
    booktitle = "The 7th Workshop on Open-Source {A}rabic Corpora and Processing Tools ({OSACT}7) with 5 Shared Tasks",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-nlpsi/2026.osact-1.21/",
    doi = "10.63317/2vdvaesuziyj",
    pages = "179--184",
    abstract = "This paper describes our system submitted to the OSACT7 AdabEval shared task on Arabic politeness detection (TaskA). The task requires classifying Arabic texts into three categories: Polite, Impolite, and Neutral. We systematically explore multiple approaches, progressing from classical machine learning baselines using pre-trained embeddings to fine-tuned transformer models. Our best system leverages MARBERT, a transformer model pre-trained on one billion Arabic tweets, fine-tuned with Focal Loss to handle the significant class imbalance present in the dataset (70{\%} Neutral). We additionally experiment with hybrid approaches combining fine-tuned embeddings with gradient-boosted classifiers and ensemble methods. Our best single model achieves a macro F1 score of 0.84 and an accuracy of 0.90 on the validation set, substantially outperforming classical ML baselines (F1 = 0.42)."
}