@inproceedings{alsuhaibani-alkaoud-2026-uslub,
    title = "Uslub at {A}bjad{A}uthor{ID} Shared Task: A Comparative Analysis of Traditional Machine Learning and Transformer-Based Models for Authorship Attribution in {A}rabic and {U}rdu",
    author = "Alsuhaibani, Shahad  and
      Alkaoud, Mohamed",
    booktitle = "Proceedings of the 2nd Workshop on {NLP} for Languages Using {A}rabic Script",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.abjadnlp-1.65/",
    pages = "515--519",
    abstract = "Authorship attribution is a critical task in natural language processing with applications ranging from forensic linguistics to plagiarism detection. While well-studied in high-resource languages, it remains challenging for low-resource languages like Arabic and Urdu. In this paper, we present our participation in the AbjadNLP shared task, where we systematically evaluate three distinct approaches: traditional machine learning using SVM with TF-IDF features, fine-tuned transformer-based models (AraBERT), and LLMs. We demonstrate that while fine-tuned AraBERT excels in Arabic, traditional lexical models (SVM) prove more robust for Urdu, outperforming both BERT-based and LLM approaches. We also show that few-shot prompting with LLMs, when operated as a reranker over top candidates, significantly outperforms zero-shot baselines. Our final systems achieved competitive performance, ranking 6th and 1st in the Arabic and Urdu tasks respectively."
}