@InProceedings{hilte-daelemans-vandekerckhove:2018:WASSA2018,
  author    = {Hilte, Lisa  and  Daelemans, Walter  and  Vandekerckhove, Reinhild},
  title     = {Predicting Adolescents' Educational Track from Chat Messages on Dutch Social Media},
  booktitle = {Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
  month     = {October},
  year      = {2018},
  address   = {Brussels, Belgium},
  publisher = {Association for Computational Linguistics},
  pages     = {328--334},
  abstract  = {We aim to predict Flemish adolescents' educational track based on their Dutch social media writing. We distinguish between the three main types of Belgian secondary education: General (theory-oriented), Vocational (practice-oriented), and Technical Secondary Education (hybrid). The best results are obtained with a Naive Bayes model, i.e. an F-score of 0.68 (std. dev. 0.05) in 10-fold cross-validation experiments on the train data and an F-score of 0.60 on unseen data. Many of the most informative features are character n-grams containing specific occurrences of chatspeak phenomena such as emoticons. While the detection of the most theory- and practice-oriented educational tracks seems to be a relatively easy task, the hybrid Technical level appears to be much harder to capture based on online writing style, as expected.},
  url       = {http://aclweb.org/anthology/W18-6248}
}