@inproceedings{zhao-etal-2025-bridging,
title = "Bridging Modality Gap for Effective Multimodal Sentiment Analysis in Fashion-related Social Media",
author = "Zhao, Zheyu and
Wang, Zhongqing and
Li, Shichen and
Wang, Hongling and
Zhou, Guodong",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.123/",
pages = "1813--1823",
abstract = "Multimodal sentiment analysis for fashion-related social media is essential for understanding how consumers appraise fashion products across platforms like Instagram and Twitter, where both textual and visual elements contribute to sentiment expression. However, a notable challenge in this task is the modality gap, where the different information density between text and images hinders effective sentiment analysis. In this paper, we propose a novel multimodal framework that addresses this challenge by introducing pseudo data generated by a two-stage framework. We further utilize a multimodal fusion approach that efficiently integrates the information from various modalities for sentiment classification of fashion posts. Experiments conducted on a comprehensive dataset demonstrate that our framework significantly outperforms existing unimodal and multimodal baselines, highlighting its effectiveness in bridging the modality gap for more accurate sentiment classification in fashion-related social media posts."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2025-bridging">
<titleInfo>
<title>Bridging Modality Gap for Effective Multimodal Sentiment Analysis in Fashion-related Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shichen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongling</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guodong</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal sentiment analysis for fashion-related social media is essential for understanding how consumers appraise fashion products across platforms like Instagram and Twitter, where both textual and visual elements contribute to sentiment expression. However, a notable challenge in this task is the modality gap, where the different information density between text and images hinders effective sentiment analysis. In this paper, we propose a novel multimodal framework that addresses this challenge by introducing pseudo data generated by a two-stage framework. We further utilize a multimodal fusion approach that efficiently integrates the information from various modalities for sentiment classification of fashion posts. Experiments conducted on a comprehensive dataset demonstrate that our framework significantly outperforms existing unimodal and multimodal baselines, highlighting its effectiveness in bridging the modality gap for more accurate sentiment classification in fashion-related social media posts.</abstract>
<identifier type="citekey">zhao-etal-2025-bridging</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.123/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>1813</start>
<end>1823</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging Modality Gap for Effective Multimodal Sentiment Analysis in Fashion-related Social Media
%A Zhao, Zheyu
%A Wang, Zhongqing
%A Li, Shichen
%A Wang, Hongling
%A Zhou, Guodong
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F zhao-etal-2025-bridging
%X Multimodal sentiment analysis for fashion-related social media is essential for understanding how consumers appraise fashion products across platforms like Instagram and Twitter, where both textual and visual elements contribute to sentiment expression. However, a notable challenge in this task is the modality gap, where the different information density between text and images hinders effective sentiment analysis. In this paper, we propose a novel multimodal framework that addresses this challenge by introducing pseudo data generated by a two-stage framework. We further utilize a multimodal fusion approach that efficiently integrates the information from various modalities for sentiment classification of fashion posts. Experiments conducted on a comprehensive dataset demonstrate that our framework significantly outperforms existing unimodal and multimodal baselines, highlighting its effectiveness in bridging the modality gap for more accurate sentiment classification in fashion-related social media posts.
%U https://aclanthology.org/2025.coling-main.123/
%P 1813-1823
Markdown (Informal)
[Bridging Modality Gap for Effective Multimodal Sentiment Analysis in Fashion-related Social Media](https://aclanthology.org/2025.coling-main.123/) (Zhao et al., COLING 2025)
ACL