@inproceedings{mohamed-eida-etal-2024-well,
    title = "How Well Do Tweets Represent Sub-Dialects of {E}gyptian {A}rabic?",
    author = "Mohamed Eida, Mai  and
      Nassar, Mayar  and
      Dunn, Jonathan",
    editor = {Scherrer, Yves  and
      Jauhiainen, Tommi  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Zampieri, Marcos  and
      Nakov, Preslav  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.vardial-1.4/",
    doi = "10.18653/v1/2024.vardial-1.4",
    pages = "41--55",
    abstract = "How well does naturally-occurring digital text, such as Tweets, represent sub-dialects of Egyptian Arabic (EA)? This paper focuses on two EA sub-dialects: Cairene Egyptian Arabic (CEA) and Sa{'}idi Egyptian Arabic (SEA). We use morphological markers from ground-truth dialect surveys as a distance measure across four geo-referenced datasets. Results show that CEA markers are prevalent as expected in CEA geo-referenced tweets, while SEA markers are limited across SEA geo-referenced tweets. SEA tweets instead show a prevalence of CEA markers and higher usage of Modern Standard Arabic. We conclude that corpora intended to represent sub-dialects of EA do not accurately represent sub-dialects outside of the Cairene variety. This finding calls into question the validity of relying on tweets alone to represent dialectal differences."
}