Mining Product Features from Online Reviews

Abstract

With the advance of the Internet, e-commerce systems have become extremely important and convenient to human being. More and more products are sold on the web, and more and more people are purchasing products online. As a result, an increasing number of customers post product reviews at merchant websites and express their opinions and experiences in any network space such as Internet forums, discussion groups, and blogs. So there is a large amount of data records related to products on the Web, which are useful for both manufacturers and customers. Mining product reviews becomes a hot research topic, and prior researches mostly base on product features to analyze the opinions. So mining product features is the first step to further reviews processing. In this paper, we present how to mine product features. The proposed extraction approach is different from the previous methods because we only mine the features of the product in opinion sentences which the customers have expressed their positive or negative experiences on. In order to find opinion sentence, a SentiWordNet-based algorithm is proposed. There are three steps to perform our task: (1) identifying opinion sentences in each review which is positive or negative via SentiWordNet; (2) mining product features that have been commented on by customers from opinion sentences; (3) pruning feature to remove those incorrect features. Compared to previous work, our experimental result achieves higher precision and recall.