|International Conference on “Internet of Things, Next Generation Networks and Cloud Computing"
|Foundation of Computer Science USA
|ICINC2017 - Number 1
|Authors: Chandana Oak, Manisha Patil
Chandana Oak, Manisha Patil . Effective Co-extraction of Online Opinion Reviews and Product Aspect Ranking. International Conference on “Internet of Things, Next Generation Networks and Cloud Computing". ICINC2017, 1 (July 2018), 5-9.
As the popularity of e-commerce is increasing day by day, many customers have started buying their products online through e-commerce sites. Customers also normally review and rate the products they have bought over multiple review sites, social networking sites, blogs, etc. Such online reviews are of great help to people who are going for that product in decision making and also to manufacturers/sellers to get immediate feedback about the product quality or after sales service, etc. Since the number of reviews for a product is usually large, it is very difficult to read all the reviews and form an opinion about the product. Also, there are multiple sources of these online reviews. Hence, online review mining is gaining importance. Another feature that can add to review usefulness is ranking the product aspects as per their importance and popularity. Ranking product aspects manually is very difficult since a product may have hundreds of features. So, an automated method to do this is needed. This paper presents a methodology for online review mining as well as for product feature ranking. The paper proposes use of Naïve Bayes Classifier for product review category classification, partial parsing of classified reviews and an algorithm to co-extract opinion target and corresponding opinion words. It also proposes an algorithm for product aspect ranking using the extracted opinion target and word pairs.