@inproceedings{chen-etal-2025-mixture,
title = "Mixture of Multimodal Adapters for Sentiment Analysis",
author = "Chen, Kezhou and
Wang, Shuo and
Ben, Huixia and
Tang, Shengeng and
Hao, Yanbin",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.90/",
doi = "10.18653/v1/2025.naacl-long.90",
pages = "1822--1833",
ISBN = "979-8-89176-189-6",
abstract = "Pre-trained language model (PLM) have achieved great success in text sentiment analysis. However, in practical applications, sentiment is not only conveyed through language but also hidden in other modalities. Therefore, multimodal sentiment analysis (MSA) has attracted increasing research interest. Compared to text sentiment analysis, MSA is challenging since (1) emotions hidden in body movements or vocal timbres eclipse traditional analytical methods, and (2) transferring PLM to MSA task requires huge training parameters. Thus, to solve these issues, we introduce the Mixture of Multimodal Adapters (MMA) into the PLM. Specifically, we first design a mixture-of-multimodal-experts module to capture and fuse emotional movements from different data. Meanwhile, we use a compression parameter for each expert to reduce the training burden. We apply our method to two benchmark datasets and achieve state-of-the-art performance with a tiny trainable parameter count. For example, compared to the current state-of-the-art method, AcFormer, we only need 1/22 of its training parameters amount (130M$\rightarrow$6M) to achieve better results."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2025-mixture">
<titleInfo>
<title>Mixture of Multimodal Adapters for Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kezhou</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huixia</namePart>
<namePart type="family">Ben</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengeng</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanbin</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Pre-trained language model (PLM) have achieved great success in text sentiment analysis. However, in practical applications, sentiment is not only conveyed through language but also hidden in other modalities. Therefore, multimodal sentiment analysis (MSA) has attracted increasing research interest. Compared to text sentiment analysis, MSA is challenging since (1) emotions hidden in body movements or vocal timbres eclipse traditional analytical methods, and (2) transferring PLM to MSA task requires huge training parameters. Thus, to solve these issues, we introduce the Mixture of Multimodal Adapters (MMA) into the PLM. Specifically, we first design a mixture-of-multimodal-experts module to capture and fuse emotional movements from different data. Meanwhile, we use a compression parameter for each expert to reduce the training burden. We apply our method to two benchmark datasets and achieve state-of-the-art performance with a tiny trainable parameter count. For example, compared to the current state-of-the-art method, AcFormer, we only need 1/22 of its training parameters amount (130M\rightarrow6M) to achieve better results.</abstract>
<identifier type="citekey">chen-etal-2025-mixture</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.90</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.90/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>1822</start>
<end>1833</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mixture of Multimodal Adapters for Sentiment Analysis
%A Chen, Kezhou
%A Wang, Shuo
%A Ben, Huixia
%A Tang, Shengeng
%A Hao, Yanbin
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F chen-etal-2025-mixture
%X Pre-trained language model (PLM) have achieved great success in text sentiment analysis. However, in practical applications, sentiment is not only conveyed through language but also hidden in other modalities. Therefore, multimodal sentiment analysis (MSA) has attracted increasing research interest. Compared to text sentiment analysis, MSA is challenging since (1) emotions hidden in body movements or vocal timbres eclipse traditional analytical methods, and (2) transferring PLM to MSA task requires huge training parameters. Thus, to solve these issues, we introduce the Mixture of Multimodal Adapters (MMA) into the PLM. Specifically, we first design a mixture-of-multimodal-experts module to capture and fuse emotional movements from different data. Meanwhile, we use a compression parameter for each expert to reduce the training burden. We apply our method to two benchmark datasets and achieve state-of-the-art performance with a tiny trainable parameter count. For example, compared to the current state-of-the-art method, AcFormer, we only need 1/22 of its training parameters amount (130M\rightarrow6M) to achieve better results.
%R 10.18653/v1/2025.naacl-long.90
%U https://aclanthology.org/2025.naacl-long.90/
%U https://doi.org/10.18653/v1/2025.naacl-long.90
%P 1822-1833
Markdown (Informal)
[Mixture of Multimodal Adapters for Sentiment Analysis](https://aclanthology.org/2025.naacl-long.90/) (Chen et al., NAACL 2025)
ACL
- Kezhou Chen, Shuo Wang, Huixia Ben, Shengeng Tang, and Yanbin Hao. 2025. Mixture of Multimodal Adapters for Sentiment Analysis. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1822–1833, Albuquerque, New Mexico. Association for Computational Linguistics.