@inproceedings{solorio-etal-2014-sockpuppet,
    title = "Sockpuppet Detection in {W}ikipedia: A Corpus of Real-World Deceptive Writing for Linking Identities",
    author = "Solorio, Thamar  and
      Hasan, Ragib  and
      Mizan, Mainul",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Loftsson, Hrafn  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
    month = may,
    year = "2014",
    address = "Reykjavik, Iceland",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/fix-sig-urls/L14-1006/",
    pages = "1355--1358",
    abstract = "This paper describes a corpus of sockpuppet cases from Wikipedia. A sockpuppet is an online user account created with a fake identity for the purpose of covering abusive behavior and/or subverting the editing regulation process. We used a semi-automated method for crawling and curating a dataset of real sockpuppet investigation cases. To the best of our knowledge, this is the first corpus available on real-world deceptive writing. We describe the process for crawling the data and some preliminary results that can be used as baseline for benchmarking research. The dataset has been released under a Creative Commons license from our project website (\url{http://docsig.cis.uab.edu/tools-and-datasets/})."
}