SentiMM: A Multimodal Multi-Agent Framework for Sentiment Analysis in Social Media

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Xilai, Zhao, Zilin, Song, Chengye, Wang, Zining, Qiang, Jinhe, Yan, Jiongrui, Lin, Yuhuai
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866911121010589696
author	Xu, Xilai Zhao, Zilin Song, Chengye Wang, Zining Qiang, Jinhe Yan, Jiongrui Lin, Yuhuai
author_facet	Xu, Xilai Zhao, Zilin Song, Chengye Wang, Zining Qiang, Jinhe Yan, Jiongrui Lin, Yuhuai
contents	With the increasing prevalence of multimodal content on social media, sentiment analysis faces significant challenges in effectively processing heterogeneous data and recognizing multi-label emotions. Existing methods often lack effective cross-modal fusion and external knowledge integration. We propose SentiMM, a novel multi-agent framework designed to systematically address these challenges. SentiMM processes text and visual inputs through specialized agents, fuses multimodal features, enriches context via knowledge retrieval, and aggregates results for final sentiment classification. We also introduce SentiMMD, a large-scale multimodal dataset with seven fine-grained sentiment categories. Extensive experiments demonstrate that SentiMM achieves superior performance compared to state-of-the-art baselines, validating the effectiveness of our structured approach.
format	Preprint
id	arxiv_https___arxiv_org_abs_2508_18108
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	SentiMM: A Multimodal Multi-Agent Framework for Sentiment Analysis in Social Media Xu, Xilai Zhao, Zilin Song, Chengye Wang, Zining Qiang, Jinhe Yan, Jiongrui Lin, Yuhuai Computation and Language With the increasing prevalence of multimodal content on social media, sentiment analysis faces significant challenges in effectively processing heterogeneous data and recognizing multi-label emotions. Existing methods often lack effective cross-modal fusion and external knowledge integration. We propose SentiMM, a novel multi-agent framework designed to systematically address these challenges. SentiMM processes text and visual inputs through specialized agents, fuses multimodal features, enriches context via knowledge retrieval, and aggregates results for final sentiment classification. We also introduce SentiMMD, a large-scale multimodal dataset with seven fine-grained sentiment categories. Extensive experiments demonstrate that SentiMM achieves superior performance compared to state-of-the-art baselines, validating the effectiveness of our structured approach.
title	SentiMM: A Multimodal Multi-Agent Framework for Sentiment Analysis in Social Media
topic	Computation and Language
url	https://arxiv.org/abs/2508.18108