@InProceedings{xu-EtAl:2018:WASSA2018,
  author    = {Xu, Peng  and  Madotto, Andrea  and  Wu, Chien-Sheng  and  Park, Ji Ho  and  Fung, Pascale},
  title     = {Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training},
  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     = {292--298},
  abstract  = {In this paper, we propose Emo2Vec which encodes emotional semantics into vectors. We train Emo2Vec by multi-task learning six different emotion-related tasks, including emotion/sentiment analysis, sarcasm classification, stress detection, abusive language classification, insult detection, and personality recognition. Our evaluation on Emo2Vec shows that it outperforms existing affect-related representations, such as Sentiment-Specific Word Embedding and DeepMoji embeddings with much smaller training corpora. When concatenated with GloVe, Emo2Vec achieves competitive performances to state-of-the-art results on several tasks using simple logistic regression classifier. Finally, we visualize the learned vectors, showing that Emo2Vec can cluster words with similar emotion together.},
  url       = {http://aclweb.org/anthology/W18-6243}
}