Open Access

ARTICLE

TGICP: A Text-Gated Interaction Network with Inter-Sample Commonality Perception for Multimodal Sentiment Analysis

Erlin Tian¹, Shuai Zhao^2,*, Min Huang², Yushan Pan^3,4, Yihong Wang^3,4, Zuhe Li¹

1 School of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou, 450002, China
2 School of Software, Zhengzhou University of Light Industry, Zhengzhou, 450002, China
3 Department of Computing, Xi’an Jiaotong-Liverpool University, Suzhou, 215123, China
4 Department of Computer Science, University of Liverpool, Liverpool, L69 7ZX, UK

* Corresponding Author: Shuai Zhao. Email:

Computers, Materials & Continua 2025, 85(1), 1427-1456. https://doi.org/10.32604/cmc.2025.066476

Received 09 April 2025; Accepted 03 July 2025; Issue published 29 August 2025

Abstract

With the increasing importance of multimodal data in emotional expression on social media, mainstream methods for sentiment analysis have shifted from unimodal to multimodal approaches. However, the challenges of extracting high-quality emotional features and achieving effective interaction between different modalities remain two major obstacles in multimodal sentiment analysis. To address these challenges, this paper proposes a Text-Gated Interaction Network with Inter-Sample Commonality Perception (TGICP). Specifically, we utilize a Inter-sample Commonality Perception (ICP) module to extract common features from similar samples within the same modality, and use these common features to enhance the original features of each modality, thereby obtaining a richer and more complete multimodal sentiment representation. Subsequently, in the cross-modal interaction stage, we design a Text-Gated Interaction (TGI) module, which is text-driven. By calculating the mutual information difference between the text modality and nonverbal modalities, the TGI module dynamically adjusts the influence of emotional information from the text modality on nonverbal modalities. This helps to reduce modality information asymmetry while enabling full cross-modal interaction. Experimental results show that the proposed model achieves outstanding performance on both the CMU-MOSI and CMU-MOSEI baseline multimodal sentiment analysis datasets, validating its effectiveness in emotion recognition tasks.

---

Keywords

---