@inproceedings{sanders-2012-collecting,
    title = "Collecting and Analysing Chats and Tweets in {S}o{N}a{R}",
    author = "Sanders, Eric",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Do{\u{g}}an, Mehmet U{\u{g}}ur  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}`12)",
    month = may,
    year = "2012",
    address = "Istanbul, Turkey",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/L12-1215/",
    pages = "2253--2256",
    abstract = "In this paper a collection of chats and tweets from the Netherlands and Flanders is described. The chats and tweets are part of the freely available SoNaR corpus, a 500 million word text corpus of the Dutch language. Recruitment, metadata, anonymisation and IPR issues are discussed. To illustrate the difference of language use between the various text types and other parameters (like gender and age) simple text analysis in the form of unigram frequency lists is carried out. Furthermore a website is presented with which users can retrieve their own frequency lists."
}