Applications Analyzing E-commerce Reviews with Large Language Models (LLMs): A Methodological Exploration and Application Insight

Abstract

The ubiquity of online shopping has transformed our daily lives, offering unparalleled convenience and enriching our purchasing experiences. It has become an indispensable part of our existence, allowing us to acquire everything from basic essentials to high-end luxury items with ease. Amazon, a leading e-commerce platform [1], employs two primary customer feedback mechanisms: the Star Rate (1-5) and detailed reviews. The Star Rate is a quick, convenient, and visually intuitive method for customers to score products, while reviews provide a more comprehensive description of the product and their shopping experience. These feedback mechanisms not only influence other users' purchasing decisions but also serve as a guide for businesses to adjust their offerings based on customer opinions, establishing a negative feedback adjustment mechanism.[2,3,4,5,6]. We introduce the innovative LLM model, commonly used in computer vision, into our NLP text analysis. Utilizing WORD2vec, we pass word vectors through classification functions to analyze pessimistic and optimistic sentiments. We then correlate these emotions with Star Rates, discovering a higher-order functional relationship between them.