Exploring Interpretability in Deep Learning for Affective Computing: A Comprehensive Review
ACM Transactions on Multimedia Computing, Communications, and Applications · 2025-07-31 · 21 (7) · 1-28
DOI: 10.1145/3723005 ↗At a glance
Journal article in ACM Transactions on Multimedia Computing, Communications, and Applications, published online on 2025-07-19. Written by Xinjie Zhang and 4 co-authors. Cited 16 times so far (Crossref); 155 references. Funded by: National Natural Science Foundation of China, Beijing Natural Science Foundation.
Abstract (original language)
Deep learning has shown impressive performance in affective computing, but its black-box characteristic limits the model’s interpretability, posing a challenge to further development and application. Compared with objective recognition tasks such as image recognition, emotion perception as a high-level cognition is more subjective, making it particularly important to enhance the interpretability of deep learning in affective computing. In recent years, some interpretability-related works have emerged, but there are few reviews on this topic yet. This article summarizes the explainable deep learning methods in affective computing from two aspects: first, the application of general explainable deep learning methods in affective computing from the perspectives of model-agnostic and model-specific is introduced; second, emotion-specific interpretability research that combines emotional psychology theories, physiological studies, and human cognition, covering task design, model design, and result analysis methods, is systematically reviewed. There are new explainable deep learning methods for multimodal and large language models in the context of emotion. Finally, we discuss five specific challenges and propose corresponding future directions to provide insights and references for subsequent research on affective computing interpretability.
Funding
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
Cite
APA
Zhang, X., Zhang, T., Sun, L., Zhao, J., & Jin, Q. (2025). Exploring Interpretability in Deep Learning for Affective Computing: A Comprehensive Review. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(7), 1-28. https://doi.org/10.1145/3723005
Vancouver
Zhang X, Zhang T, Sun L, Zhao J, Jin Q. Exploring Interpretability in Deep Learning for Affective Computing: A Comprehensive Review. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(7):1-28. doi:10.1145/3723005
BibTeX
@article{Zhang2025,
author = {Zhang, Xinjie and Zhang, Tenggan and Sun, Lei and Zhao, Jinming and Jin, Qin},
title = {Exploring Interpretability in Deep Learning for Affective Computing: A Comprehensive Review},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2025},
volume = {21},
number = {7},
pages = {1--28},
doi = {10.1145/3723005}
}
EUVIMED