@inproceedings{ljubesic-etal-2017-language,
    title = "Language-independent Gender Prediction on {T}witter",
    author = "Ljube{\v{s}}i{\'c}, Nikola  and
      Fi{\v{s}}er, Darja  and
      Erjavec, Toma{\v{z}}",
    editor = {Hovy, Dirk  and
      Volkova, Svitlana  and
      Bamman, David  and
      Jurgens, David  and
      O{'}Connor, Brendan  and
      Tsur, Oren  and
      Do{\u{g}}ru{\"o}z, A. Seza},
    booktitle = "Proceedings of the Second Workshop on {NLP} and Computational Social Science",
    month = aug,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W17-2901",
    doi = "10.18653/v1/W17-2901",
    pages = "1--6",
    abstract = "In this paper we present a set of experiments and analyses on predicting the gender of Twitter users based on language-independent features extracted either from the text or the metadata of users{'} tweets. We perform our experiments on the TwiSty dataset containing manual gender annotations for users speaking six different languages. Our classification results show that, while the prediction model based on language-independent features performs worse than the bag-of-words model when training and testing on the same language, it regularly outperforms the bag-of-words model when applied to different languages, showing very stable results across various languages. Finally we perform a comparative analysis of feature effect sizes across the six languages and show that differences in our features correspond to cultural distances.",
}