STATISTICAL AND SENTIMENT ANALYSIS OF CONSUMER PRODUCT REVIEWS

Big Data commerce has given a big leap to e-commerce. It has opened up the avenues to smarter and informed decision making for large industries as well as the consumers. Online reviews on e-commerce giants like Amazon, Flipkart are one such paradigm which can be used to arrive at more profitable decisions. They are not only beneficial for the consumers but also for the product manufacturers. Online reviews have the potential to provide an insight to the buyers about the product like its quality, performance and recommendations; thereby providing a clear picture of the product to the future buyers. The usefulness of online reviews for manufacturers to realize customer requirements by analyzing helpful reviews is one such unrealized potential. Both positive and negative reviews play a big role in determining the customer requirements and extracting consumer's feedback about the product faster. Sentiment Analysis is a computational study to extract subjective information from the text. In this research, data analysis of a large set of online reviews for mobile phones is conducted. We have not only classified the text into positive and negative sentiment but have also included sentiments of anger, anticipation, disgust, fear, joy, sadness, surprise and trust. This delineated classification of reviews is helpful to evaluate the product holistically, enabling better-decision making for consumers.