Enhancing Cognitive Models of Emotions with Representation Learning
This work addresses the problem of computationally describing psychological emotion models for researchers in affective computing and psychology, though it appears incremental in applying representation learning to this domain.
The authors developed a deep learning framework to create embedding representations of fine-grained emotions for computational psychological models, achieving state-of-the-art results by classifying 32 emotions on the Empathetic Dialogue dataset.
We present a novel deep learning-based framework to generate embedding representations of fine-grained emotions that can be used to computationally describe psychological models of emotions. Our framework integrates a contextualized embedding encoder with a multi-head probing model that enables to interpret dynamically learned representations optimized for an emotion classification task. Our model is evaluated on the Empathetic Dialogue dataset and shows the state-of-the-art result for classifying 32 emotions. Our layer analysis can derive an emotion graph to depict hierarchical relations among the emotions. Our emotion representations can be used to generate an emotion wheel directly comparable to the one from Plutchik's\LN model, and also augment the values of missing emotions in the PAD emotional state model.