Adaptive Multimodal Sentiment Analysis with Stream-Based Active Learning for Spoken Dialogue Systems

Atsuto Ajichi, Takato Hayashi, Kazunori Komatani, Shogo Okada


Abstract
In empathic dialogue systems, it is crucial to continuously monitor and adapt to the user’s emotional state. To capture user-specific mappings between multimodal behaviors and emotional states, directly asking users about their emotions during dialogue is the most straightforward and effective approach. However, frequent questioning can cause inconvenience to users and diminish the user experience, so the number of queries should be minimized. In this study, we formulate personalized multimodal sentiment analysis (MSA) as a stream-based active learning problem, where user behaviors are observed sequentially, and we assume that the system has an ability to decide at each step whether to request an emotion label from the user. Simulation experiments using a human–agent dialogue corpus demonstrate that the proposed method efficiently improves performance even under few-shot conditions. These results indicate that our approach is effective for developing dialogue systems that achieve cost-efficient personalized MSA.
Anthology ID:
2026.iwsds-1.33
Volume:
Proceedings of the 16th International Workshop on Spoken Dialogue System Technology
Month:
February
Year:
2026
Address:
Trento, Italy
Editors:
Giuseppe Riccardi, Seyed Mahed Mousavi, Maria Ines Torres, Koichiro Yoshino, Zoraida Callejas, Shammur Absar Chowdhury, Yun-Nung Chen, Frederic Bechet, Joakim Gustafson, Géraldine Damnati, Alex Papangelis, Luis Fernando D’Haro, John Mendonça, Raffaella Bernardi, Dilek Hakkani-Tur, Giuseppe "Pino" Di Fabbrizio, Tatsuya Kawahara, Firoj Alam, Gokhan Tur, Michael Johnston
Venue:
IWSDS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
326–337
Language:
URL:
https://aclanthology.org/2026.iwsds-1.33/
DOI:
Bibkey:
Cite (ACL):
Atsuto Ajichi, Takato Hayashi, Kazunori Komatani, and Shogo Okada. 2026. Adaptive Multimodal Sentiment Analysis with Stream-Based Active Learning for Spoken Dialogue Systems. In Proceedings of the 16th International Workshop on Spoken Dialogue System Technology, pages 326–337, Trento, Italy. Association for Computational Linguistics.
Cite (Informal):
Adaptive Multimodal Sentiment Analysis with Stream-Based Active Learning for Spoken Dialogue Systems (Ajichi et al., IWSDS 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.iwsds-1.33.pdf