Aim

          To automatically identify the sentiment for each and every product based on user reviews with improved efficiency and improved business solutions and services.

Abstract  

          Sentiment Analysis is the process of determining whether a piece of writing is positive, negative or neutral. Machine learning (ML) is a type of artificial intelligence (AI) that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning algorithms use historical data as input to predict new output values. In this project, we calculate the sentiment of every particular product which is in the e-commerce applications by processing the user reviews. By calculating the sentiment for all the products through the process of sentiment analysis for reviews with any domains, we can analyze the top selling products in those applications. By analyzing the products, the retailer can predict the value of each and every product in their e-commerce applications.

Proposed System

In the proposed system, a sentiment classifier is proposed for emotion detection of the users or the consumers based on the reviews they upload in the e-commerce applications. By analyzing those reviews, we can identify the status of a product and its importance over the users. In this system, we will be having two e-commerce applications with different domains, such as textiles and mobiles respectively. Where the users will register and login in an e-commerce application. Then, the users will select the category of products they need to buy and add the products to their cart along with the quantity of those products. The users can add reviews about the products based on their experience with those products after buying them. The bank admin will login using the admin name and password. Then, the admin will add the users and also credit money for the users according to the amount they deposit. Then, the user will proceed with the payment for those products they added in their cart in the e-commerce application. Finally, the admin will login and can view the total users in the applications and the currently active users. In the pre-process, the text will get trained for the sentiment analysis process. In the chunker process, the calculations of positive, negative and neutral reviews for each and every product which are in different domains will get processed. Then, the sentiment analysis chart for all the reviews of the products will get displayed for the admin as the result of chunker process. Thus, the admin can understand the details of the products.