@inproceedings{van-der-lee-van-den-bosch-2017-exploring,
    title = "Exploring Lexical and Syntactic Features for Language Variety Identification",
    author = "van der Lee, Chris  and
      van den Bosch, Antal",
    editor = {Nakov, Preslav  and
      Zampieri, Marcos  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Tiedemann, J{\"o}rg  and
      Malmasi, Shevin  and
      Ali, Ahmed},
    booktitle = "Proceedings of the Fourth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial)",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W17-1224/",
    doi = "10.18653/v1/W17-1224",
    pages = "190--199",
    abstract = "We present a method to discriminate between texts written in either the Netherlandic or the Flemish variant of the Dutch language. The method draws on a feature bundle representing text statistics, syntactic features, and word $n$-grams. Text statistics include average word length and sentence length, while syntactic features include ratios of function words and part-of-speech $n$-grams. The effectiveness of the classifier was measured by classifying Dutch subtitles developed for either Dutch or Flemish television. Several machine learning algorithms were compared as well as feature combination methods in order to find the optimal generalization performance. A machine-learning meta classifier based on AdaBoost attained the best F-score of 0.92."
}