@inproceedings{mohamed-eida-habash-2025-beyond,
    title = "Beyond {C}airo: {S}a{'}idi {E}gyptian {A}rabic Literary Corpus Construction and Analysis",
    author = "Mohamed Eida, Mai  and
      Habash, Nizar",
    editor = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      {\"O}hman, Emily  and
      Bizzoni, Yuri  and
      Miyagawa, So  and
      Alnajjar, Khalid},
    booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
    month = may,
    year = "2025",
    address = "Albuquerque, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.nlp4dh-1.26/",
    pages = "292--304",
    ISBN = "979-8-89176-234-3",
    abstract = "Egyptian Arabic (EA) NLP resources have mainly focused on Cairene Egyptian Arabic (CEA), leaving sub-dialects like Sa{'}idi Egyptian Arabic (SEA) underrepresented. This paper introduces the first SEA corpus {--} an open-source, 4-million-word literary dataset of a dialect spoken by {\textasciitilde}30 million Egyptians. To validate its representation, we analyze SEA-specific linguistic features from dialectal surveys, confirming a higher prevalence in our corpus compared to existing EA datasets. Our findings offer insights into SEA{'}s orthographic representation in morphology, phonology, and lexicon, incorporating CODA* guidelines for normalization."
}