Abstract: With the growing trend of e-commerce sites, blogs and web forums, people are keenly articulating their opinion on various products, topics. If we are buying a product for the first time, we would go through reviews which are already presented by the users who have used it. Manual analysis can be difficult and consumes more time, thus, a method is required to present the summary of the reviews. Reviews recorded by the users are unstructured in nature. Opinion mining is a discipline of web content mining which in turn is a category of web mining. The other categories of web mining are web structure and web usage mining. Opinion mining can be exploited by both companies and individuals. It involves natural language processing, text analysis and computational linguistics. The focus of the proposed system is mainly in extracting the aspects or features of the product which is the first step of opinion mining. An extension to the Intrinsic and Extrinsic Domain relevance method is made in order to support the rare features too. If the extraction step is improvised, the consequent steps will give fine grained outcomes and thus the result will be enhanced greatly.
G. Bharathi Mohan and T. Ravi, 2016. Finding Infrequent Features During Feature Extraction in Opinion Mining Using Fuzzy Based Clustering. Asian Journal of Information Technology, 15: 4546-4550.