A Feature Based Approach for Sentiment Analysis by Using Support Vector Machine
D. V. Nagarjuna Devi, Chinta Kishore Kumar, S. Naga Prasad · 2016
In this modern era of globalization, e-commerce has become one of the most convenient ways to shop. Every day people buy many products through online and post their reviews about the product which they have used. These reviews play a vital role in determining how far a product has been placed in consumers' psyche. So that the manufacturer can modify the features of the product as required and on the other hand these will also help the new consumers to decide on whether to buy the product or not. However, it would be a tedious task to manually extract overall opinion out of enormous unstructured data. This problem can be addressed by an automated system called 'Sentiment Analysis and Opinion Mining' that can analyze and extract the users' perception in the whole reviews. In our work we have developed an overall process of 'Aspect or Feature based Sentiment Analysis' by using a classifier called Support Vector Machine (SVM) in a novel approach. It is proved to be one of the most effective ways to analyze and extract the overall users' view about the particular feature and whole product as well.