@inproceedings{ljubesic-fiser-2016-private,
    title = "Private or Corporate? Predicting User Types on {T}witter",
    author = "Ljube{\v{s}}i{\'c}, Nikola  and
      Fi{\v{s}}er, Darja",
    editor = "Han, Bo  and
      Ritter, Alan  and
      Derczynski, Leon  and
      Xu, Wei  and
      Baldwin, Tim",
    booktitle = "Proceedings of the 2nd Workshop on Noisy User-generated Text ({WNUT})",
    month = dec,
    year = "2016",
    address = "Osaka, Japan",
    publisher = "The COLING 2016 Organizing Committee",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W16-3904/",
    pages = "4--12",
    abstract = "In this paper we present a series of experiments on discriminating between private and corporate accounts on Twitter. We define features based on Twitter metadata, morphosyntactic tags and surface forms, showing that the simple bag-of-words model achieves single best results that can, however, be improved by building a weighted soft ensemble of classifiers based on each feature type. Investigating the time and language dependence of each feature type delivers quite unexpecting results showing that features based on metadata are neither time- nor language-insensitive as the way the two user groups use the social network varies heavily through time and space."
}