IPMMSA: MODELLING AN IMPROVED PROMPT-BASED MULTI-MODAL SENTIMENT ANALYSIS OVER FASHION DATASETS

Abstract

To enhance pertinent decision-making in a variety of applications, prompt-based sentiment analysis attempts to leverage cross-modal opinion signals to analyze users’ attitude direction regarding the specific attribute. Even though many techniques have been created, they are unable to use multiple knowledge types at once and are unable to successfully eliminate unwanted signals from various viewpoints, which can impair multimodal representations' discriminative power and keep models from performing better. To fill up the research gaps, this work suggests an improved prompt-based multi-modal sentiment analysis (IPMMSA) strategy that incorporates multi-view and diversified knowledge augmentation. In particular, it implements fine-grained image-aspect interactions by transforming the image into an underlying sequence of embedding’s which makes filtering easier from a visual semantic standpoint. Attribute-guided vision-language interactions are then used to pull out important extract affective signals and suppress irrelevant content within a multimodal semantic framework, while the network structure is formulated to effectively exploit context-informed semantic fusion, syntactic relations, and sentiment-aware domain knowledge. Ultimately, the model yields robust and expressive multimodal embedding’s to boost aspect-based sentiment analysis performance during multimodal integration with multi-modal fashion dataset. Finally, to show the superiority along with efficacy of our suggested approach extensive experiments were conducted on two widely used multi-modal fashion datasets.