Dimensional Emotion Detection from Categorical Emotion

Sungjoon Park, Jiseon Kim, Seonghyeon Ye, Jaeyeol Jeon, Hee Young Park, Alice Oh


Abstract
We present a model to predict fine-grained emotions along the continuous dimensions of valence, arousal, and dominance (VAD) with a corpus with categorical emotion annotations. Our model is trained by minimizing the EMD (Earth Mover’s Distance) loss between the predicted VAD score distribution and the categorical emotion distributions sorted along VAD, and it can simultaneously classify the emotion categories and predict the VAD scores for a given sentence. We use pre-trained RoBERTa-Large and fine-tune on three different corpora with categorical labels and evaluate on EmoBank corpus with VAD scores. We show that our approach reaches comparable performance to that of the state-of-the-art classifiers in categorical emotion classification and shows significant positive correlations with the ground truth VAD scores. Also, further training with supervision of VAD labels leads to improved performance especially when dataset is small. We also present examples of predictions of appropriate emotion words that are not part of the original annotations.
Anthology ID:
2021.emnlp-main.358
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4367–4380
Language:
URL:
https://aclanthology.org/2021.emnlp-main.358
DOI:
10.18653/v1/2021.emnlp-main.358
Bibkey:
Cite (ACL):
Sungjoon Park, Jiseon Kim, Seonghyeon Ye, Jaeyeol Jeon, Hee Young Park, and Alice Oh. 2021. Dimensional Emotion Detection from Categorical Emotion. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4367–4380, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Dimensional Emotion Detection from Categorical Emotion (Park et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.358.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.358.mp4
Code
 sungjoonpark/emotiondetection
Data
EmoBankISEAR