Optimizing Online Shopping: Leveraging Llama for Product Review Summarization
Roshani Parate · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 2024
This article highlights a unique "Customer Satisfaction Analysis" module and presents an innovative online commodity search system. The system's goal is to rapidly retrieve product data such as search results, product details, and reviews—through e-commerce API endpoints and display it in an intuitive user interface. The "Customer Satisfaction Analysis" section is particularly noteworthy as it utilizes sophisticated algorithms to examine customer feedback and produce detailed summaries that accentuate the salient features of user opinion. This methodology endows prospective purchasers with a more profound and perceptive comprehension of product attributes and client contentment. Sentiment analysis is integrated into the search process, allowing consumers to make well-informed buying selections. Our approach improves consumers' capacity to make decisions by synthesizing product features and user feedback. This allows consumers to make better educated choices and ultimately have a more fulfilling online shopping experience. Key Words: API, Large Language Model , Llama, Search System