Resolving Sentiment Discrepancy for Multimodal Sentiment Detection via Semantics Completion and Decomposition

TL;DR

This paper introduces a novel CoDe network that addresses sentiment discrepancy in multimodal (image-text) posts by completing and decomposing semantics, leading to improved sentiment detection accuracy.

Contribution

The paper proposes a semantics completion and decomposition framework that explicitly models and leverages sentiment discrepancies between image and text modalities.

Findings

Outperforms existing methods on four datasets

Effectively captures discrepant sentiments between modalities

Improves unimodal encoding and fusion for sentiment detection

Abstract

With the proliferation of social media posts in recent years, the need to detect sentiments in multimodal (image-text) content has grown rapidly. Since posts are user-generated, the image and text from the same post can express different or even contradictory sentiments, leading to potential \textbf{sentiment discrepancy}. However, existing works mainly adopt a single-branch fusion structure that primarily captures the consistent sentiment between image and text. The ignorance or implicit modeling of discrepant sentiment results in compromised unimodal encoding and limited performance. In this paper, we propose a semantics Completion and Decomposition (CoDe) network to resolve the above issue. In the semantics completion module, we complement image and text representations with the semantics of the in-image text, helping bridge the sentiment gap. In the semantics decomposition module, we decompose image and text representations with exclusive projection and contrastive learning, thereby explicitly capturing the discrepant sentiment between modalities. Finally, we fuse image and text representations by cross-attention and combine them with the learned discrepant sentiment for final classification. Extensive experiments on four datasets demonstrate the superiority of CoDe and the effectiveness of each proposed module.