Sentiment analysis based product rating using textual reviews

With the rapid growth of web technology there is a huge amount of data present in the web for internet users. Such data is mainly from the social media such as Facebook [4], twitter, etc., where millions of people express their views in their daily interaction which can be their sentiments or opinions about a particular thing. Large amount of data also present in the forms of reviews and ratings in many online shopping websites such as Amazon, Flip cart, snap deal etc., In order to automate the analysis of such data the area of Sentiment analysis is used. Before performing sentiment analysis the data is subjected to many pre-processing techniques and then identifying opinion data in the reviews and classifying them according to their polarity confidence i.e., whether they fall under positive or negative or neutral connotation. The open source data tool analysis tool called rapid miner is used to perform the step by step explanation of review processing. This paper also presents a comparative study of algorithms like SVM and Naïve Bayes.