@inproceedings{fromreide-etal-2014-crowdsourcing,
    title = "Crowdsourcing and annotating {NER} for {T}witter {\#}drift",
    author = "Fromreide, Hege  and
      Hovy, Dirk  and
      S{\o}gaard, Anders",
    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/jlcl-multiple-ingestion/L14-1361/",
    pages = "2544--2547",
    abstract = "We present two new NER datasets for Twitter; a manually annotated set of 1,467 tweets (kappa=0.942) and a set of 2,975 expert-corrected, crowdsourced NER annotated tweets from the dataset described in Finin et al. (2010). In our experiments with these datasets, we observe two important points: (a) language drift on Twitter is significant, and while off-the-shelf systems have been reported to perform well on in-sample data, they often perform poorly on new samples of tweets, (b) state-of-the-art performance across various datasets can be obtained from crowdsourced annotations, making it more feasible to {\textquotedblleft}catch up{\textquotedblright} with language drift."
}