Next Article in Journal
Novel Bio-Optoelectronics Enabled by Flexible Micro Light-Emitting Diodes
Next Article in Special Issue
Multitasking Learning Model Based on Hierarchical Attention Network for Arabic Sentiment Analysis Classification
Previous Article in Journal
Optimized Device Geometry of Normally-On Field-Plate AlGaN/GaN High Electron Mobility Transistors for High Breakdown Performance Using TCAD Simulation
Previous Article in Special Issue
Fine-Grained Implicit Sentiment in Financial News: Uncovering Hidden Bulls and Bears
Article

Mixing and Matching Emotion Frameworks: Investigating Cross-Framework Transfer Learning for Dutch Emotion Detection

Language and Translation Technology Team, Ghent University, 9000 Ghent, Belgium
*
Author to whom correspondence should be addressed.
Academic Editor: Miguel A. Alonso
Electronics 2021, 10(21), 2643; https://doi.org/10.3390/electronics10212643
Received: 30 September 2021 / Revised: 26 October 2021 / Accepted: 27 October 2021 / Published: 29 October 2021
(This article belongs to the Special Issue Emerging Application of Sentiment Analysis Technologies)
Emotion detection has become a growing field of study, especially seeing its broad application potential. Research usually focuses on emotion classification, but performance tends to be rather low, especially when dealing with more advanced emotion categories that are tailored to specific tasks and domains. Therefore, we propose the use of the dimensional emotion representations valence, arousal and dominance (VAD), in an emotion regression task. Firstly, we hypothesize that they can improve performance of the classification task, and secondly, they might be used as a pivot mechanism to map towards any given emotion framework, which allows tailoring emotion frameworks to specific applications. In this paper, we examine three cross-framework transfer methodologies: multi-task learning, in which VAD regression and classification are learned simultaneously; meta-learning, where VAD regression and emotion classification are learned separately and predictions are jointly used as input for a meta-learner; and a pivot mechanism, which converts the predictions of the VAD model to emotion classes. We show that dimensional representations can indeed boost performance for emotion classification, especially in the meta-learning setting (up to 7% macro F1-score compared to regular emotion classification). The pivot method was not able to compete with the base model, but further inspection suggests that it could be efficient, provided that the VAD regression model is further improved. View Full-Text
Keywords: emotion detection; multi-task learning; transfer learning; emotion frameworks emotion detection; multi-task learning; transfer learning; emotion frameworks
Show Figures

Figure 1

MDPI and ACS Style

De Bruyne, L.; De Clercq, O.; Hoste, V. Mixing and Matching Emotion Frameworks: Investigating Cross-Framework Transfer Learning for Dutch Emotion Detection. Electronics 2021, 10, 2643. https://doi.org/10.3390/electronics10212643

AMA Style

De Bruyne L, De Clercq O, Hoste V. Mixing and Matching Emotion Frameworks: Investigating Cross-Framework Transfer Learning for Dutch Emotion Detection. Electronics. 2021; 10(21):2643. https://doi.org/10.3390/electronics10212643

Chicago/Turabian Style

De Bruyne, Luna, Orphée De Clercq, and Véronique Hoste. 2021. "Mixing and Matching Emotion Frameworks: Investigating Cross-Framework Transfer Learning for Dutch Emotion Detection" Electronics 10, no. 21: 2643. https://doi.org/10.3390/electronics10212643

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop