Cross-modal Sentiment Analysis of Text Image Fusion Based on Hybrid Fusion Strategy

Abstract

Due to the different modalities of data such as images and text, the difficulty of sentiment analysis increases. Therefore, a cross-modal sentiment analysis method based on text image fusion is established in this study. In the experiment, a bidirectional network is used to extract text and image features. On this basis, a cross-modal sentiment analysis method based on image text fusion is established. At the same time, concepts such as image attributes are introduced in the experiment to detect irony in graphic and textual data. Finally, a hybrid strategy cross-modal sentiment analysis method is established in the experiment. After comparison, the proposed research method has the highest subject working characteristic curve and PR, which are 5% and 3% higher than the comparative methods, respectively. When the validation set size is 400, the recognition time of the proposed research method is 2.1 seconds. When iterating 50, the recognition time of this method is 0.9 seconds. In practical applications, the proposed research method has accurately analyzed six types of graphic and textual content with different emotional tendencies. This method has the best detection results for both single graphic and cross-modal modes.