Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
This work addresses the need for generalized emotion representations in natural language processing, offering an incremental improvement over existing methods.
The authors tackled the problem of encoding emotional semantics into vectors by proposing Emo2Vec, trained via multi-task learning on six emotion-related tasks, and found that it outperforms existing affect-related representations with smaller training corpora and achieves competitive state-of-the-art results when combined with GloVe.
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.