SENTIMENT ANALYSIS USING ONLINE PRODUCT REVIEWS

Abstract

Sentiment analysis gained the close attention in the recent years and it is the main task of Natural Language Processing (NLP). The aim of this paper focuses to handle the problem of sentiment polarity categorization, which is the basic problem of Sentiment Analysis. We have tried to propose a general process for sentiment polarity categorization and support vector machine is used for classifying the polarity of sentences. Reviews collected from online product reviews collected from Amazon.com are the data used. The outcomes are promising for both sentence-level categorization and review-level categorization.