@inproceedings{scheffler-2014-german,
    title = "A {G}erman {T}witter Snapshot",
    author = "Scheffler, Tatjana",
    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/ingest-emnlp/L14-1101/",
    pages = "2284--2289",
    abstract = "We present a new corpus of German tweets. Due to the relatively small number of German messages on Twitter, it is possible to collect a virtually complete snapshot of German twitter messages over a period of time. In this paper, we present our collection method which produced a 24 million tweet corpus, representing a large majority of all German tweets sent in April, 2013. Further, we analyze this representative data set and characterize the German twitterverse. While German Twitter data is similar to other Twitter data in terms of its temporal distribution, German Twitter users are much more reluctant to share geolocation information with their tweets. Finally, the corpus collection method allows for a study of discourse phenomena in the Twitter data, structured into discussion threads."
}