Primary Emotions and Recognition of Their Intensities. (30th January 2020)

• Record Type: Journal Article
• Authors: Afdhal, Rim; Ejbali, Ridha; Zaied, Mourad
• Editors: Murtagh, Fionn
• Is Part Of: Computer journal. Volume 64:Number 12(2021)
• Page Start: 1848
• Page End: 1860
• Publication Date: 2020-01-30
• Subjects: primary emotions -- intensities -- feature extraction -- classification -- deep learning -- fuzzy logic; Computers -- Periodicals; 005.1
• DOI: 10.1093/comjnl/bxz162
• Languages: English
• ISSNs: 0010-4620

Abstract

Abstract: The emotion recognition field has two major issues. On the one hand, it is difficult to find the same emotion state in different persons since they may express the same emotion state in various ways. On the other hand, it is also hard to seek the difference between expressions of the same person because some emotion states are too subtle to discriminate. The focus of this work is to solve these two problems by proposing a new approach of emotion recognition. This novel approach allows our emotion recognition system to classify 18 emotions (primary emotions and their intensities). First, we proposed textual definitions of the intensity emotions. Then, we created our emotion recognition system, which is composed of three stages: pre-treatment, feature extraction and classification. We used the deep learning for the feature extraction and the fuzzy logic for the classification. The experimental test demonstrates the efficiency of our system for primary emotions and their intensities' classification compared to other methods.