GateMABSA: Aspect-Image Gated Fusion for Multimodal Aspect-based Sentiment Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lawan, Adamu, Yunusa, Haruna
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912615190495232
author Lawan, Adamu
Yunusa, Haruna
author_facet Lawan, Adamu
Yunusa, Haruna
contents Aspect-based Sentiment Analysis (ABSA) has recently advanced into the multimodal domain, where user-generated content often combines text and images. However, existing multimodal ABSA (MABSA) models struggle to filter noisy visual signals, and effectively align aspects with opinion-bearing content across modalities. To address these challenges, we propose GateMABSA, a novel gated multimodal architecture that integrates syntactic, semantic, and fusion-aware mLSTM. Specifically, GateMABSA introduces three specialized mLSTMs: Syn-mLSTM to incorporate syntactic structure, Sem-mLSTM to emphasize aspect--semantic relevance, and Fuse-mLSTM to perform selective multimodal fusion. Extensive experiments on two benchmark Twitter datasets demonstrate that GateMABSA outperforms several baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25037
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GateMABSA: Aspect-Image Gated Fusion for Multimodal Aspect-based Sentiment Analysis
Lawan, Adamu
Yunusa, Haruna
Computation and Language
Aspect-based Sentiment Analysis (ABSA) has recently advanced into the multimodal domain, where user-generated content often combines text and images. However, existing multimodal ABSA (MABSA) models struggle to filter noisy visual signals, and effectively align aspects with opinion-bearing content across modalities. To address these challenges, we propose GateMABSA, a novel gated multimodal architecture that integrates syntactic, semantic, and fusion-aware mLSTM. Specifically, GateMABSA introduces three specialized mLSTMs: Syn-mLSTM to incorporate syntactic structure, Sem-mLSTM to emphasize aspect--semantic relevance, and Fuse-mLSTM to perform selective multimodal fusion. Extensive experiments on two benchmark Twitter datasets demonstrate that GateMABSA outperforms several baselines.
title GateMABSA: Aspect-Image Gated Fusion for Multimodal Aspect-based Sentiment Analysis
topic Computation and Language
url https://arxiv.org/abs/2509.25037