Convolutional neural networks method for analysis of e-commerce customer reviews

Sentiment Analysis (SA) is the most common text classification tool that analyses an incoming message and tells whether the underlying sentiment is positive, negative, or neutral. E-Commerce portals are generating a lot of data every day in the form of customer reviews. It extracts subjective information in source material and helping a business to understand the social sentiment of their brand, product, or service while monitoring online conversations. Many sentiment analysis techniques are available and most of them are done using a single machine learning algorithm. This paper proposes a method of extracting text features using a Convolutional neural network and uses logistic regression to analyze the sentiment polarity of the customer reviews. The result of the experimental result proves that this model effectively improves the performance of the sentimental classification.