Targeted aspect based multimodal sentiment analysis:an attention capsule extraction and multi-head fusion network

TL;DR

This paper introduces a novel targeted aspect-based multimodal sentiment analysis framework using an attention capsule extraction and multi-head fusion network, effectively capturing interactions among text, image, and context for improved sentiment understanding.

Contribution

It proposes the first targeted aspect-based multimodal sentiment analysis model with an innovative EF-Net combining attention capsules and multi-head fusion.

Findings

Effective sentiment analysis on two datasets

Improved interaction modeling among modalities

Demonstrated superiority over baseline methods

Abstract

Multimodal sentiment analysis has currently identified its significance in a variety of domains. For the purpose of sentiment analysis, different aspects of distinguishing modalities, which correspond to one target, are processed and analyzed. In this work, we propose the targeted aspect-based multimodal sentiment analysis (TABMSA) for the first time. Furthermore, an attention capsule extraction and multi-head fusion network (EF-Net) on the task of TABMSA is devised. The multi-head attention (MHA) based network and the ResNet-152 are employed to deal with texts and images, respectively. The integration of MHA and capsule network aims to capture the interaction among the multimodal inputs. In addition to the targeted aspect, the information from the context and the image is also incorporated for sentiment delivered. We evaluate the proposed model on two manually annotated datasets. the experimental results demonstrate the effectiveness of our proposed model for this new task.