Mixing and Matching Emotion Frameworks: Investigating Cross-Framework Transfer Learning for Dutch Emotion Detection
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 to... Mehr ...
Verfasser: | |
---|---|
Dokumenttyp: | Text |
Erscheinungsdatum: | 2021 |
Verlag/Hrsg.: |
Multidisciplinary Digital Publishing Institute
|
Schlagwörter: | emotion detection / multi-task learning / transfer learning / emotion frameworks |
Sprache: | Englisch |
Permalink: | https://search.fid-benelux.de/Record/base-27415778 |
Datenquelle: | BASE; Originalkatalog |
Powered By: | BASE |
Link(s) : | https://doi.org/10.3390/electronics10212643 |
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.