SENTIMENTAL ANALYSIS FOR USER REVIEWS USING DUAL SENTIMENT ANALYSIS TECHNIQUES

Abstract

Sentiment analysis or opinion mining aims to detect subjective information such as opinions, attitudes, and feelings
expressed in text by the people. Opinion mining would process a set of search results for a given item, generating a list of
product attributes like its quality, features; and aggregating opinions about each of them like poor, mixed, good. Then it will
identify the unique properties of this problem and develop a method for automatically distinguishing between positive,
negative and neutral reviews. Sentiment analysis gathers the public opinions and reviews. Dual sentiment analysis considers
two sides of one review. It is used to analyze the user reviews for the product. Sentiment analysis is used for tracking the
mood of the public about a particular product or topic using natural language processing. Sentiment analysis is also called
as opinion mining it involves in building a system which collect and examine opinions about the product made in comments,
reviews, or tweets. With the vast growth of the social media contents and online shopping sites on the Internet in the past few
years, people now express their opinion on almost anything. Searching the user opinions on sites and monitoring them on the
web is difficult task. Thus there is a need for automatic opinion Sentiment Analysis is the area of study that analyzes customer
feedback, opinions, sentiments, evaluations, attitudes, and from written language. It is one of the most useful research areas
in Natural Language Processing and is also widely studied in data mining. The importance of sentiment analysis coincides
with the growth of social media such as reviews, discussion forums, blogs, and social networks. Additionally this system adds
the hit count and the buy count features so as to find the number of users who have visited the site and purchased the product.
The objective of this feature is to know the amount of people who have browsed the product and have not purchased, this will
register in the hit count class. If a particular person bought the product this will make sure that it gets registered in the buy
count. The main idea is to let the potential customer know the amount of people who have just browsed the product and the
people who have scrolled through the product. This will give an in detail depth knowledge and the popularity of these
product.