@InProceedings{felbo-EtAl:2017:EMNLP2017,
  author    = {Felbo, Bjarke  and  Mislove, Alan  and  S{\o}gaard, Anders  and  Rahwan, Iyad  and  Lehmann, Sune},
  title     = {Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {1615--1625},
  abstract  = {NLP tasks are often limited by scarcity of manually annotated data. In social
	media sentiment analysis and related tasks, researchers have therefore used
	binarized emoticons and specific hashtags as forms of distant supervision. Our
	paper shows that by extending the distant supervision to a more diverse set of
	noisy labels, the models can learn richer representations. Through emoji
	prediction on a dataset of 1246 million tweets containing one of 64 common
	emojis we obtain state-of-the-art performance on 8 benchmark datasets
	within emotion, sentiment and sarcasm detection using a single pretrained
	model. Our analyses confirm that the diversity of our emotional labels yield a
	performance improvement over previous distant supervision approaches.},
  url       = {https://www.aclweb.org/anthology/D17-1169}
}