Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
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.
Cite
@article{arxiv.1809.04505,
title = {Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training},
author = {Peng Xu and Andrea Madotto and Chien-Sheng Wu and Ji Ho Park and Pascale Fung},
journal= {arXiv preprint arXiv:1809.04505},
year = {2018}
}
Comments
Accepted by 9th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis(WASSA) in EMNLP 2018