A Survey of Sentiment Analysis Based on Customer Reviews in Deep Learning

Abstract

Online reviews have gained popularity as they help people make decisions. In this context, the goal of this project is to develop a deep learning platform that can be used to classify customer feedback as positive or negative. This process is known as sentiment analysis. It is based on a supervised learning mechanism where a classifier is built on knowledge of the training data and then used to classify the test data. A prototype application is being built to demonstrate proof of concept. The success of deep learning largely depends on the availability of large-scale training data. A new deep learning framework for review classification using public ratings as weak observation signals. To this end, an algorithm called Deep Learning Sentiment Analysis (DLSA) is proposed and implemented. An application prototype was created to demonstrate this concept, and an empirical study of showed that the proposed system outperforms the current system.