@inproceedings{tschuggnall-etal-2019-reduce,
    title = "Reduce {\&} Attribute: Two-Step Authorship Attribution for Large-Scale Problems",
    author = {Tschuggnall, Michael  and
      Murauer, Benjamin  and
      Specht, G{\"u}nther},
    editor = "Bansal, Mohit  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/K19-1089/",
    doi = "10.18653/v1/K19-1089",
    pages = "951--960",
    abstract = "Authorship attribution is an active research area which has been prevalent for many decades. Nevertheless, the majority of approaches consider problem sizes of a few candidate authors only, making them difficult to apply to recent scenarios incorporating thousands of authors emerging due to the manifold means to digitally share text. In this study, we focus on such large-scale problems and propose to effectively reduce the number of candidate authors before applying common attribution techniques. By utilizing document embeddings, we show on a novel, comprehensive dataset collection that the set of candidate authors can be reduced with high accuracy. Moreover, we show that common authorship attribution methods substantially benefit from a preliminary reduction if thousands of authors are involved."
}