Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Xinyu, Lin, Yuming, He, Lihua, Li, You, Chang, Liang, Zhou, Ya
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912060851355648
author Feng, Xinyu
Lin, Yuming
He, Lihua
Li, You
Chang, Liang
Zhou, Ya
author_facet Feng, Xinyu
Lin, Yuming
He, Lihua
Li, You
Chang, Liang
Zhou, Ya
contents Multimodal Sentiment Analysis (MSA) utilizes multimodal data to infer the users' sentiment. Previous methods focus on equally treating the contribution of each modality or statically using text as the dominant modality to conduct interaction, which neglects the situation where each modality may become dominant. In this paper, we propose a Knowledge-Guided Dynamic Modality Attention Fusion Framework (KuDA) for multimodal sentiment analysis. KuDA uses sentiment knowledge to guide the model dynamically selecting the dominant modality and adjusting the contributions of each modality. In addition, with the obtained multimodal representation, the model can further highlight the contribution of dominant modality through the correlation evaluation loss. Extensive experiments on four MSA benchmark datasets indicate that KuDA achieves state-of-the-art performance and is able to adapt to different scenarios of dominant modality.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04491
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis
Feng, Xinyu
Lin, Yuming
He, Lihua
Li, You
Chang, Liang
Zhou, Ya
Computation and Language
Artificial Intelligence
Multimedia
Multimodal Sentiment Analysis (MSA) utilizes multimodal data to infer the users' sentiment. Previous methods focus on equally treating the contribution of each modality or statically using text as the dominant modality to conduct interaction, which neglects the situation where each modality may become dominant. In this paper, we propose a Knowledge-Guided Dynamic Modality Attention Fusion Framework (KuDA) for multimodal sentiment analysis. KuDA uses sentiment knowledge to guide the model dynamically selecting the dominant modality and adjusting the contributions of each modality. In addition, with the obtained multimodal representation, the model can further highlight the contribution of dominant modality through the correlation evaluation loss. Extensive experiments on four MSA benchmark datasets indicate that KuDA achieves state-of-the-art performance and is able to adapt to different scenarios of dominant modality.
title Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis
topic Computation and Language
Artificial Intelligence
Multimedia
url https://arxiv.org/abs/2410.04491