VSE knjižnice (vzajemna bibliografsko-kataložna baza podatkov COBIB.SI)
  • Language-independent gender prediction on Twitter [Elektronski vir]
    Ljubešić, Nikola, 1979- ; Fišer, Darja, 1978- ; Erjavec, Tomaž, 1960-
    In this paper we present a set of experiments and analyses on predicting the gender of Twitter users based on languageindependent 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.
    Vir: Proceedings of the Second Workshop on Natural Language Processing and Computational Social Science [Elektronski vir] (Str. 1-6)
    Vrsta gradiva - prispevek na konferenci
    Leto - 2017
    Jezik - angleški
    COBISS.SI-ID - 65025378

    Povezava(-e):

    http://www.aclweb.org/anthology/W/W17/W17-29.pdf

Vnos na polico