AN EXPERIMENTAL ANALYSIS ON ECOMMERCE REVIEWS,WITH SENTIMENT CLASSIFICATION USING OPINION MINING ON WEB

Abstract

Sentiment analysis is a big branch in the field of natural language processing. Sentiment analysis mainly text based analysis, but there are some challenges that make it difficult as compared to traditional text based analysis. This paper empathizes on the need of an attempt to improve research process and progress of sentiment analysis on the basis of investigation. Outcome of the analysis are summarized in this paper. This paper analyze the reviews of products manually by collecting data in the form of a excel file. Then it will produce and classify the reviews as positive or negative comments to get the best product. Now it’s more relevant to automate reviews data it is growing exponentially. This method works by web scrapping reviews from e-commerce website. Data cleaning is applied to remove the unwanted data known as stop words. The features are identified. The feature can be camera, battery life etc. Obtain frequency across all the products and for all the reviews per feature. The intended work is to extract the features from the reviews and detecting the polarity for each aspect, thus resulting in feature extraction matrix (FEM). FEM matrix has each row as an observation for a product and each of the columns represent the feature. List of Products based on highest value of FEM for searched features and product recommendations are generated based on the user searched feature.