@InProceedings{groot-EtAl:2018:S18-1,
  author    = {Groot, Daphne  and  Kruizinga, Rémon  and  Veldthuis, Hennie  and  de Wit, Simon  and  Haagsma, Hessel},
  title     = {PickleTeam! at SemEval-2018 Task 2: English and Spanish Emoji Prediction from Tweets},
  booktitle = {Proceedings of The 12th International Workshop on Semantic Evaluation},
  month     = {June},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {454--458},
  abstract  = {We present a system for emoji prediction on English and Spanish tweets, prepared for the SemEval-2018 task on Multilingual Emoji Prediction. We compared the performance of an SVM, LSTM and an ensemble of these two. We found the SVM performed best on our development set with an accuracy of 61.3% for English and 83% for Spanish. The features used for the SVM are lowercased word n-grams in the range of 1 to 20, tokenised by a TweetTokenizer and stripped of stop words. On the test set, our model achieved an accuracy of 34% on English, with a slightly lower score of 29.7% accuracy on Spanish.},
  url       = {http://www.aclweb.org/anthology/S18-1072}
}