Abstract
Aspect-based multimodal sentiment analysis (ABMSA) is an emerging task in the research of multimodal sentiment analysis, which aims to identify the sentiment of each aspect mentioned in multimodal sample. Although recent research on ABMSA has achieved some success, most existing models only adopt attention mechanism to interact aspect with text and image respectively and obtain sentiment output through multimodal concatenation, they often neglect to consider that some samples may not have semantic relevance between text and image. In this article, we propose a Text-Image Semantic Relevance Identification (TISRI) model for ABMSA to address the problem. Specifically, we introduce a multimodal feature relevance identification module to calculate the semantic similarity between text and image, and then construct an image gate to dynamically control the input image information. On this basis, an image auxiliary information is provided to enhance the semantic expression ability of visual feature representation to generate more intuitive image representation. Furthermore, we employ attention mechanism during multimodal feature fusion to obtain the text-aware image representation through text-image interaction to prevent irrelevant image information interfering our model. Experiments demonstrate that TISRI achieves competitive results on two ABMSA Twitter datasets, and then validate the effectiveness of our methods.