On the benefits of using Hidden Markov Models to predict emotions

Wu, Yuyuan; Arevalillo-Herráez, Miguel; Katsigiannis, Stamos; Ramzan, Naeem

Abstract

The availability of low-cost wireless physiological sensors has allowed the use of emotion recognition technologies in various applications. In this work, we describe a technique to predict emotional states in Russell’s two-dimensional emotion space (valence and arousal), using electroencephalography (EEG), electrocardiography (ECG), and electromyography (EMG) signals. For each of the two dimensions, the proposed method uses a classification scheme based on two Hidden Markov Models (HMMs), with the first one trained using positive samples, and the second one using negative samples. The class of new unseen samples is then decided based on which model returns the highest score. The proposed approach was validated on a recently published dataset that contained physiological signals recordings (EEG, ECG, EMG) acquired during a human-horse interaction experiment. The experimental results demonstrate that this approach achieves a better performance than the published baseline methods, achieving an F1-score of 0.940 for valence and 0.783 for arousal, an improvement of more than +0.12 in both cases.

Citation

Wu, Y., Arevalillo-Herráez, M., Katsigiannis, S., & Ramzan, N. (2022, July). On the benefits of using Hidden Markov Models to predict emotions. Presented at ACM Conference on User Modeling, Adaptation and Personalization (UMAP), Barcelona

• Presentation Conference Type: Conference Paper (published)
• Conference Name: ACM Conference on User Modeling, Adaptation and Personalization (UMAP)
• Start Date: Jul 4, 2022
• End Date: Jul 7, 2022
• Acceptance Date: Apr 11, 2022
• Online Publication Date: Jul 4, 2022
• Publication Date: 2022-07
• Deposit Date: Apr 25, 2022
• Publicly Available Date: Apr 25, 2022
• Pages: 164-169
• DOI: https://doi.org/10.1145/3503252.3531323
• Public URL: https://durham-repository.worktribe.com/output/1137270