@inproceedings{nguyen-etal-2026-wikifirst,
    title = "{W}iki{F}irst: A Genre-Fixed, Content-controlled Corpus for Evaluating Content Effects in Authorship Analysis",
    author = "Nguyen, Dung Tuan  and
      Sat, G. {\c{C}}a{\u{g}}atay  and
      Pyshkin, Evgeny  and
      Blake, John",
    editor = "Alves, Diego  and
      Bizzoni, Yuri  and
      Degaetano-Ortlieb, Stefania  and
      Kazantseva, Anna  and
      Pagel, Janis  and
      Szpakowicz, Stan",
    booktitle = "Proceedings of the 10th Joint {SIGHUM} Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/bulk-corrections-2026-07-02/2026.latechclfl-1.31/",
    doi = "10.18653/v1/2026.latechclfl-1.31",
    pages = "323--327",
    ISBN = "979-8-89176-373-9",
    abstract = "This paper presents the design and construction of WikiFirst, a corpus for investigating the impact of content variation on authorship similarity under a fixed genre. Prior work has investigated individual authorial style and impact of genre. However, the role of content has remained underexplored due to the lack of suitable data. We address this gap by constructing a Wikipedia-based corpus consisting exclusively of first revisions authored by non-anonymous editors, thereby ensuring high authorship certainty while maintaining a stable encyclopaedic genre."
}