@InProceedings{koper-kim-klinger:2017:WASSA2017,
  author    = {K\"{o}per, Maximilian  and  Kim, Evgeny  and  Klinger, Roman},
  title     = {IMS at EmoInt-2017: Emotion Intensity Prediction with Affective Norms, Automatically Extended Resources and Deep Learning},
  booktitle = {Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {50--57},
  abstract  = {Our submission to the WASSA-2017 shared task on the prediction of emotion
	intensity in tweets is a supervised learning method with extended lexicons of
	affective norms. We combine three main information sources in a random forrest
	regressor, namely (1), manually created resources, (2) automatically extended
	lexicons, and (3) the output of a neural network (CNN-LSTM) for sentence
	regression. All three feature sets perform similarly well in isolation (≈ .67
	macro average Pearson correlation). The combination achieves .72 on the
	official test set (ranked 2nd out of 22 participants). Our analysis reveals
	that performance is increased by providing cross-emotional intensity
	predictions. The
	automatic extension of lexicon features benefit from domain specific
	embeddings.
	Complementary ratings for affective norms increase the impact of lexicon
	features. Our resources (ratings for 1.6 million twitter specific words) and
	our implementation is publicly available at
	http://www.ims.uni-stuttgart.de/data/ims\_emoint.},
  url       = {http://www.aclweb.org/anthology/W17-5206}
}