Abstract
Our study employs sentiment analysis to evaluate the compatibility of Amazon.com reviews with their corresponding ratings. Sentiment analysis is the task of identifying and classifying the sentiment expressed in a piece of text as being positive or negative. On e-commerce websites such as Amazon.com, consumers can submit their reviews along with a specific polarity rating. In some instances, there is a mismatch between the review and the rating. To identify the reviews with mismatched ratings we performed sentiment analysis using deep learning on Amazon.com product review data. Product reviews were converted to vectors using paragraph vector, which then was used to train a recurrent neural network with gated recurrent unit. Our model incorporated both semantic relationship of review text and product information. We also developed a web service application that predicts the rating score for a submitted review using the trained model and if there is a mismatch between predicted rating score and submitted rating score, it provides feedback to the reviewer.
Highlights
Sentiment analysis is the task of computationally identifying and categorizing the sentiment expressed by an author in a piece of text
In order to analyse the sentiment of Amazon.com reviews we built a model using recurrent neural networks (RNN) with gated recurrent unit (GRU) that learned low-dimensional vector representation of reviews using paragraph vectors and product embeddings
We further grouped and sorted review embedding to form a product sequence which is fed to a gated recurrent unit (GRU) to learn product embedding
Summary
Sentiment analysis is the task of computationally identifying and categorizing the sentiment expressed by an author in a piece of text. It has a wide range of applications in industry from forecasting market movements based on sentiment expressed in news and blogs, to identifying customer satisfaction and dissatisfaction from their reviews and social media posts. It forms the basis for other applications like recommender systems. Consumers can assign a numerical value (i.e., rating) to the product or service they are reviewing. It is important to identify the reviews with mismatched ratings since individual ratings are used to compute the average rating
Sign-in/Register to view highlights & summary 
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call