@inproceedings{yin-etal-2025-feature,
title = "Feature Decomposition-Augmentation Network for Multimodal Sentiment Analysis",
author = "Yin, Dapeng and
Hou, Bingxuan and
Gao, Mengna and
Zhu, Shuyue and
Wang, Junli",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.6/",
pages = "86--98",
ISBN = "979-8-89176-298-5",
abstract = "Multimodal sentiment analysis identifies human emotional tendencies by analyzing text, visual, and auditory modalities. In most studies, the textual modality is usually considered to contain the most emotional information and is regarded as the dominant modality. Existing methods mostly map auxiliary modalities into a semantic space close to the dominant modality, which overly relies on the dominant modality. In this work, we propose a Feature Decomposition-Augmentation (FeaDA) framework, which aims to elevate the role of auxiliary modalities in multimodal data fusion. We first design a projector to decompose auxiliary modalities into partial features, which contain features for emotion judgment, and then utilize these decomposed features to guide the fusion process with KL loss, thereby enhancing the status of auxiliary modality fusion. To verify the effectiveness of our method, we conducted experiments on the CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets. The experimental results show that our FeaDA framework outperforms mutilmodal sentiment analysis methods of the same type in main metrics. Our code is available at https://github.com/PowerLittleYin/FeaDA-main."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yin-etal-2025-feature">
<titleInfo>
<title>Feature Decomposition-Augmentation Network for Multimodal Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dapeng</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bingxuan</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengna</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuyue</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junli</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>Multimodal sentiment analysis identifies human emotional tendencies by analyzing text, visual, and auditory modalities. In most studies, the textual modality is usually considered to contain the most emotional information and is regarded as the dominant modality. Existing methods mostly map auxiliary modalities into a semantic space close to the dominant modality, which overly relies on the dominant modality. In this work, we propose a Feature Decomposition-Augmentation (FeaDA) framework, which aims to elevate the role of auxiliary modalities in multimodal data fusion. We first design a projector to decompose auxiliary modalities into partial features, which contain features for emotion judgment, and then utilize these decomposed features to guide the fusion process with KL loss, thereby enhancing the status of auxiliary modality fusion. To verify the effectiveness of our method, we conducted experiments on the CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets. The experimental results show that our FeaDA framework outperforms mutilmodal sentiment analysis methods of the same type in main metrics. Our code is available at https://github.com/PowerLittleYin/FeaDA-main.</abstract>
<identifier type="citekey">yin-etal-2025-feature</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.6/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>86</start>
<end>98</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Feature Decomposition-Augmentation Network for Multimodal Sentiment Analysis
%A Yin, Dapeng
%A Hou, Bingxuan
%A Gao, Mengna
%A Zhu, Shuyue
%A Wang, Junli
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F yin-etal-2025-feature
%X Multimodal sentiment analysis identifies human emotional tendencies by analyzing text, visual, and auditory modalities. In most studies, the textual modality is usually considered to contain the most emotional information and is regarded as the dominant modality. Existing methods mostly map auxiliary modalities into a semantic space close to the dominant modality, which overly relies on the dominant modality. In this work, we propose a Feature Decomposition-Augmentation (FeaDA) framework, which aims to elevate the role of auxiliary modalities in multimodal data fusion. We first design a projector to decompose auxiliary modalities into partial features, which contain features for emotion judgment, and then utilize these decomposed features to guide the fusion process with KL loss, thereby enhancing the status of auxiliary modality fusion. To verify the effectiveness of our method, we conducted experiments on the CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets. The experimental results show that our FeaDA framework outperforms mutilmodal sentiment analysis methods of the same type in main metrics. Our code is available at https://github.com/PowerLittleYin/FeaDA-main.
%U https://aclanthology.org/2025.ijcnlp-long.6/
%P 86-98
Markdown (Informal)
[Feature Decomposition-Augmentation Network for Multimodal Sentiment Analysis](https://aclanthology.org/2025.ijcnlp-long.6/) (Yin et al., IJCNLP-AACL 2025)
ACL
- Dapeng Yin, Bingxuan Hou, Mengna Gao, Shuyue Zhu, and Junli Wang. 2025. Feature Decomposition-Augmentation Network for Multimodal Sentiment Analysis. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 86–98, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.