Skip to content
Book Open access

Multimodal Aspect-Based Sentiment Analysis via Evidence-Guided Region Calibration

Nov 2026 · Proceedings of the 35th ACM International Conference on Information and Knowledge Management · pp. 1872-1883 · 0 citations · 6 references

TL;DR

VEGA first leverages a multimodal large language model to construct two complementary types of visual evidence from each image-text pair: content-aware visual evidence and context-aware sentiment evidence, enabling image regions to contribute according to their roles in content understanding and sentiment inference.

Abstract

Multimodal Aspect-Based Sentiment Analysis (MABSA) aims to identify aspect-level sentiment from user-generated image-text posts. Although visual information can provide useful context for sentiment reasoning, it is not uniformly beneficial for aspect-level prediction. Different image regions may serve distinct roles: some provide content support for post understanding, some offer sentiment-related evidence, while others introduce irrelevant or misleading signals. To address this challenge, we propose VEGA, a MABSA framework that integrates visual evidence construction with evidence-guided region calibration. Specifically, VEGA first leverages a multimodal large language model to construct two complementary types of visual evidence from each image-text pair: content-aware visual evidence and context-aware sentiment evidence. These evidence streams are then used to calibrate region-level visual representations through a dual-support cross-attention mechanism, enabling image regions to contribute according to their roles in content understanding and sentiment inference. Finally, the calibrated visual features are integrated with the original text in a unified encoder-decoder architecture for both multimodal aspect sentiment classification and joint multimodal aspect-sentiment analysis subtasks. Experiments on public benchmarks demonstrate that VEGA consistently outperforms strong task-specific baselines. Further analyses confirm the effectiveness of visual evidence construction and evidence-guided region calibration.

Read PDF

Similar papers

Preprint Sep 2026

Multimodal Aspect-Level Sentiment Analysis Based on Gated Noise Filtering and Emotion-Relevance Interaction

A Gated Noise-filtered Sentiment-Relevance Interaction (GNSRI) framework that employs a gated noise-filtering module to suppress sentiment-irrelevant features and enhance aspect-aware sentiment cues, and a sentiment-relevance interaction module to capture consistent and conflicting cross-modal signals at micro and macr...

Chen Huang, Liang-Wei Guo, Ya-Min Li et al. · 0 citations
Open access Sep 2026

Label-Aware Entropic Distributional Contrastive Alignment for Multimodal Sentiment Analysis

This work proposes a label-aware distributional contrastive alignment framework that improves Acc-5 by 0.5–2.9 percentage points over the strongest baseline on each dataset and achieves the best or joint-best Acc-7 among the compared methods on CMU-MOSI and CMU-MOSEI.

Meng-Yao Wang, Xiu-Yang Meng, Chun-Ling Wang · 0 citations
Review Open access Oct 2026

Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews using Learnable Aspect Queries

The field of Multimodal Aspect-Based Sentiment Analysis (MABSA) has attracted considerable interest due to its unique ability to jointly leverage both textual and visual modalities for better aspect-level sentiment prediction. Nonetheless, there is no consideration of the dependence on particular modalities in practica...

Sneha R. Kaware, R. Shelke, P. Manjare · 0 citations
Book Open access Nov 2026

CMF-LLaVA: Causal Modality-Aware Fusion with Effect Estimation for Multimodal Aspect-Based Sentiment Analysis

Multimodal Aspect-Based Sentiment Analysis (MABSA) predicts sentiment toward a specified aspect from paired text and images. In realistic multimodal posts, however, the two modalities are often asymmetric in reliability and may even provide conflicting evidence for the queried aspect. Correlation-based fusion is theref...

Tian-Yu Zhao, Ling-Ang Meng, Da-Wei Song · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.