A reinforced self-training method achieved over 80% accuracy on dominance and arousal labels, outperforming previous techniques in few-shot emotion classification based on physiological signals in VR.
A reinforced self-training method improves emotion classification accuracy in virtual reality environments using physiological signals.
Affective computing focuses on recognizing emotions using a combination of psychology, computer science, and biomedical engineering. With virtual reality (VR) becoming more widely accessible, affective computing has become increasingly important for supporting social interactions on online virtual platforms. However, accurately estimating a person’s emotional state in VR is challenging because it differs from real-world conditions, such as the unavailability of facial expressions. This research proposes a self-training method that uses unlabeled data and a reinforcement learning approach to select and label data more accurately. Experiments on a dataset of dialogues of VR players show that the proposed method achieved an accuracy of over 80% on dominance and arousal labels and outperformed previous techniques in the few-shot classification of emotions based on physiological signals.
Liu et al. (Tue,) conducted a other in Emotion classification in virtual reality. Reinforced self-training method vs. Previous techniques was evaluated on Accuracy on dominance and arousal labels. A reinforced self-training method achieved over 80% accuracy on dominance and arousal labels, outperforming previous techniques in few-shot emotion classification based on physiological signals in VR.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: