Extended Comprehensive Sentiment Analysis for Informal Opinion Text

Abstract

There has been a remarkable increase in use of E-commerce websites, the World Wide Web can now be seen as a repository of reviews and opinions from users spread across various websites and networks. Comprehensive feedback about the product can help the company know what the users liked and disliked about their product. People tend to adapt modern writing styles like misspelled words, abbreviations, concatenated words and emoticons, considering these can increase the accuracy of sentiment analysis. Moreover people tend to use different words for a particular feature of the product. Thus, identifying frequent nouns and noun phrases automatically will help classify more number of reviews and also help in identifying any new feature of the product that is being talked about.