Towards a Multi-Dataset for Complex Emotions Learning Based on Deep Neural Networks

Billal Belainine, Fatiha Sadat, Mounir Boukadoum, Hakim Lounis


Abstract
In sentiment analysis, several researchers have used emoji and hashtags as specific forms of training and supervision. Some emotions, such as fear and disgust, are underrepresented in the text of social media. Others, such as anticipation, are absent. This research paper proposes a new dataset for complex emotion detection using a combination of several existing corpora in order to represent and interpret complex emotions based on the Plutchik’s theory. Our experiments and evaluations confirm that using Transfer Learning (TL) with a rich emotional corpus, facilitates the detection of complex emotions in a four-dimensional space. In addition, the incorporation of the rule on the reverse emotions in the model’s architecture brings a significant improvement in terms of precision, recall, and F-score.
Anthology ID:
2020.lincr-1.7
Volume:
Proceedings of the Second Workshop on Linguistic and Neurocognitive Resources
Month:
May
Year:
2020
Address:
Marseille, France
Editors:
Emmanuele Chersoni, Barry Devereux, Chu-Ren Huang
Venue:
LiNCr
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
50–58
Language:
English
URL:
https://aclanthology.org/2020.lincr-1.7
DOI:
Bibkey:
Cite (ACL):
Billal Belainine, Fatiha Sadat, Mounir Boukadoum, and Hakim Lounis. 2020. Towards a Multi-Dataset for Complex Emotions Learning Based on Deep Neural Networks. In Proceedings of the Second Workshop on Linguistic and Neurocognitive Resources, pages 50–58, Marseille, France. European Language Resources Association.
Cite (Informal):
Towards a Multi-Dataset for Complex Emotions Learning Based on Deep Neural Networks (Belainine et al., LiNCr 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lincr-1.7.pdf