A Novel Web Application of Product Recommender System based on Sentiment Analysis

In present scenario the data overload is a serious problem. for mere humans, its impossible to analyse data manually without error or bias. One prime example of this regarding the review of products on e-commerce websites is that when a customer buys a certain product, he first looks for its ratings and then decides whether to buy that item or not. But only ratings are insufficient to determine the quality of the product. Reviews give us a much clearer and more in-depth understanding of the product. There is a need to summarize the feedback in a meaningful manner. Here’s where sentimental analysis comes into play. Sentiment analysis can be automated, decisions can be made based on a significant amount of data rather than plain intuition that isn’t always right. This proposed model combines sentiment analysis and a recommendation system to provide users with a comprehensive recommendation of e-commerce products. The aim of this analysis is to determine the orientation of a review then the recommender module provides users with product recommendations by analyzing large amounts of user-supplied data that is ratings and the sentiments of users and other factors like price and the number of sales to provide the user with the best recommendation. This is developed in the Python language.