@inproceedings{meng-etal-2026-beyond-polarity,
title = "Beyond Polarity: Continuous Affect-Enhanced Multimodal Aspect-Based Sentiment Classification",
author = "Meng, Ling-Ang and
Zhao, Tianyu and
Song, Dawei and
Cao, Jingxu and
Zuo, Youhui",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1979/",
doi = "10.18653/v1/2026.findings-acl.1979",
pages = "39717--39727",
ISBN = "979-8-89176-395-1",
abstract = "Multimodal aspect-based sentiment classification (MABSC) requires aspect-level sentiment inference from textual-image data that jointly convey opinions. Yet most existing approaches primarily exploit discrete polarity patterns and generic visual embeddings, making them less effective when the affect is subtle, implicit, or expressed through imagery. In this work, we propose $\textbf{\textit{VADE}}$, a Valence{--}Arousal{--}Dominance$~(\textbf{\textit{VAD}})-\textbf{\textit{E}}$nhanced MABSC framework that brings continuous VAD signals into multimodal sentiment reasoning and learns emotion-sensitive image representations. Specifically, we design a VAD encoder to extract continuous affect cues from text for aspect-level sentiment reasoning. Furthermore, we fine-tune a CLIP-based image encoder on affect-enriched image{--}text pairs to obtain visual representations that are more sensitive to sentiment cues. To support the fine-tuning process, we construct an affect-enriched image{--}text dataset $\textbf{\textit{Senti-COCO}}$ by rewriting MSCOCO captions with a multimodal large language model, which yields large-scale image-text pairs with richer affective expressions. Experiments on two mainstream datasets, Twitter-15 and Twitter-17, show that VADE achieves a new state-of-the-art performance, demonstrating the effectiveness of incorporating VAD signals for MABSC."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meng-etal-2026-beyond-polarity">
<titleInfo>
<title>Beyond Polarity: Continuous Affect-Enhanced Multimodal Aspect-Based Sentiment Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ling-Ang</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawei</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingxu</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youhui</namePart>
<namePart type="family">Zuo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Multimodal aspect-based sentiment classification (MABSC) requires aspect-level sentiment inference from textual-image data that jointly convey opinions. Yet most existing approaches primarily exploit discrete polarity patterns and generic visual embeddings, making them less effective when the affect is subtle, implicit, or expressed through imagery. In this work, we propose VADE, a Valence–Arousal–Dominance (VAD)-Enhanced MABSC framework that brings continuous VAD signals into multimodal sentiment reasoning and learns emotion-sensitive image representations. Specifically, we design a VAD encoder to extract continuous affect cues from text for aspect-level sentiment reasoning. Furthermore, we fine-tune a CLIP-based image encoder on affect-enriched image–text pairs to obtain visual representations that are more sensitive to sentiment cues. To support the fine-tuning process, we construct an affect-enriched image–text dataset Senti-COCO by rewriting MSCOCO captions with a multimodal large language model, which yields large-scale image-text pairs with richer affective expressions. Experiments on two mainstream datasets, Twitter-15 and Twitter-17, show that VADE achieves a new state-of-the-art performance, demonstrating the effectiveness of incorporating VAD signals for MABSC.</abstract>
<identifier type="citekey">meng-etal-2026-beyond-polarity</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1979</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1979/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>39717</start>
<end>39727</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Polarity: Continuous Affect-Enhanced Multimodal Aspect-Based Sentiment Classification
%A Meng, Ling-Ang
%A Zhao, Tianyu
%A Song, Dawei
%A Cao, Jingxu
%A Zuo, Youhui
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F meng-etal-2026-beyond-polarity
%X Multimodal aspect-based sentiment classification (MABSC) requires aspect-level sentiment inference from textual-image data that jointly convey opinions. Yet most existing approaches primarily exploit discrete polarity patterns and generic visual embeddings, making them less effective when the affect is subtle, implicit, or expressed through imagery. In this work, we propose VADE, a Valence–Arousal–Dominance (VAD)-Enhanced MABSC framework that brings continuous VAD signals into multimodal sentiment reasoning and learns emotion-sensitive image representations. Specifically, we design a VAD encoder to extract continuous affect cues from text for aspect-level sentiment reasoning. Furthermore, we fine-tune a CLIP-based image encoder on affect-enriched image–text pairs to obtain visual representations that are more sensitive to sentiment cues. To support the fine-tuning process, we construct an affect-enriched image–text dataset Senti-COCO by rewriting MSCOCO captions with a multimodal large language model, which yields large-scale image-text pairs with richer affective expressions. Experiments on two mainstream datasets, Twitter-15 and Twitter-17, show that VADE achieves a new state-of-the-art performance, demonstrating the effectiveness of incorporating VAD signals for MABSC.
%R 10.18653/v1/2026.findings-acl.1979
%U https://aclanthology.org/2026.findings-acl.1979/
%U https://doi.org/10.18653/v1/2026.findings-acl.1979
%P 39717-39727
Markdown (Informal)
[Beyond Polarity: Continuous Affect-Enhanced Multimodal Aspect-Based Sentiment Classification](https://aclanthology.org/2026.findings-acl.1979/) (Meng et al., Findings 2026)
ACL