Multi-dimensional Sentiment Analysis for Large-Scale E-commerce Reviews

Abstract

E-commerce reviews reveal the customers’ attitudes on the products, which are very helpful for customers to know other people’s opinions on interested products. Meanwhile, producers are able to learn the public sentiment on their products being sold in E-commerce platforms. Generally, E-commerce reviews involve many aspects of products, e.g., appearance, quality, price, logistics, and so on. Therefore, sentiment analysis on E-commerce reviews has to cope with those different aspects. In this paper, we define each of those aspects as a dimension of product, and present a multi-dimensional sentiment analysis approach for E-commerce reviews. In particular, we employ a sentiment lexicon expanding mechanism to remove the word ambiguity among different dimensions, and propose an algorithm for sentiment analysis on E-commerce reviews based on rules and a dimensional sentiment lexicon. We conduct experiments on a large-scale dataset involving over 28 million reviews, and compare our approach with the traditional way that does not consider dimensions of reviews. The results show that the multi-dimensional approach reaches a precision of 95.5% on average, and outperforms the traditional way in terms of precision, recall, and F-measure.