Product Recommendation System using Opinion Mining

Abstract

Social media is becoming a major and popular technological platform that allows users to express personal
opinions toward the subjects with shared interests, opinion are good for decision making to People would want to know
others' opinion before taking a decision, while corporate would like to monitor pulse of people in a social media about
their products and services and take appropriate actions. This paper reviewed about world are realizing that ecommerce is not just buying and selling over Internet, rather it is improve the efficiency to compete with other giants in
the market. Their opinions on specific topic are inevitably dependent on many social effects such as user preference on
topics, peer influence, user profile information. E-Commerce sites are gaining popularity across the world. People visit
them not just to shop products but also to know the opinion of other buyers and users of products. Online customer
reviews are helping consumers to decide which products to buy and also companies to understand the buying behavior of
consumers. In this paper we have created a prototype web based system for recommending and comparing products sold
online. We have used natural language processing to automatically read reviews and used Naive Bayes classification to
determine the polarity of reviews. We have also extracted the reviews of product features and the polarity of those
features. We graphically present to the customer, the better of two products based on various criteria including the star
ratings, date of review, the helpfulness score of the review and the polarity of reviews.