MULTIMODAL ALIGNMENT AND HIERARCHICAL FUSION NETWORK FOR MULTIMODAL SENTIMENT ANALYSIS

Abstract

The widespread emergence of multimodal data on social platforms has presented new opportunities for sentiment analysis. However, previous studies have often overlooked the issue of detail loss during modal interaction fusion. They also exhibit limitations in addressing semantic alignment challenges and the sensitivity of modalities to noise. To enhance analytical accuracy, a novel model named MAHFNet is proposed. The proposed architecture is composed of three main components. Firstly, an attention-guided gated interaction alignment module is developed for modeling the semantic interaction between text and image using a gated network and a cross-modal attention mechanism. Next, a contrastive learning mechanism is introduced to encourage the aggregation of semantically aligned image-text pairs. Subsequently, an intra-modality emotion extraction module is designed to extract local emotional features within each modality. This module serves to compensate for detail loss during interaction fusion. The intra-modal local emotion features and cross-modal interaction features are then fed into a hierarchical gated fusion module, where the local features are fused through a cross-gated mechanism to dynamically adjust the contribution of each modality while suppressing modality-specific noise. Then, the fusion results and cross-modal interaction features are further fused using a multi-scale attention gating module to capture hierarchical dependencies between local and global emotional information, thereby enhancing the model’s ability to perceive and integrate emotional cues across multiple semantic levels. Finally, extensive experiments have been conducted on three public multimodal sentiment datasets, with results demonstrating that the proposed model outperforms existing methods across multiple evaluation metrics. Specifically, on the TumEmo dataset, our model achieves improvements of 2.55% in ACC and 2.63% in F1 score compared to the second-best method. On the HFM dataset, these gains reach 0.56% in ACC and 0.9% in F1 score, respectively. On the MVSA-S dataset, these gains reach 0.03% in ACC and 1.26% in F1 score. These findings collectively validate the overall effectiveness of the proposed model.