Multi Modal Image Text Sentiment Analysis Method for Social Media

Abstract

With the widespread application of social media, the multimodal fusion feature of "text + image" in user-generated content has become a dominant form. Therefore, sentiment analysis based on multimodal social media images and texts is an important research topic today. However, sentiment analysis faces three major challenges: enhancing image modality expression, bridging the cross-modal semantic gap, and improving the ability to model complex texts. This paper reviews five typical multimodal sentiment analysis methods proposed in the past two years. These methods are categorized into image enhancement, semantic alignment, and large model integration based on the types of problems they primarily address. A comparative analysis of their technical paths, performance, and application scenarios is conducted to understand the research focus of each type of model, identify their shortcomings and challenges, and propose a cross-category fusion technology solution by integrating existing model methods. An integrated framework of "universal semantic encoding + dynamic modality adaptation + cross-scenario calibration" is constructed to improve the generalization and robustness of models, providing directions for future research on multimodal social media image-text sentiment analysis.