Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training

Published in Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA), EMNLP 2018, 2018

[PDF] [Code]


@article{emo2vec,
  title={Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training},
  author={Xu, Peng and Madotto, Andrea and Wu, Chien-Sheng and Park, Jiho and Fung, Pascale},
  journal={arXiv preprint arXiv:1809.04505},
  year={2018}
}

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 of 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 a simple logistic regression classifier.