Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training

Peng Xu, Andrea Madotto, Chien-Sheng Wu, Ji Ho Park, Pascale Fung


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.
Anthology ID:
W18-6243
Volume:
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Alexandra Balahur, Saif M. Mohammad, Veronique Hoste, Roman Klinger
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
292–298
Language:
URL:
https://aclanthology.org/W18-6243
DOI:
10.18653/v1/W18-6243
Bibkey:
Cite (ACL):
Peng Xu, Andrea Madotto, Chien-Sheng Wu, Ji Ho Park, and Pascale Fung. 2018. Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 292–298, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training (Xu et al., WASSA 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6243.pdf
Code
 pxuab/emo2vec_wassa_paper
Data
SSTSST-2SST-5