Sentiment analysis using RNN model with LSTM

Abstract

In today's digital world with a rapid increase in e-commerce portals, the consumers are more oriented towards seeking out online reviews, feedback, or ratings over a product during the online buying process. In this research work, we tried to investigate the relationship between the review ratings and the sentiment of reviews in the form of their polarity. We have tried to predict the sentiments over the given reviews by implementing various machine learning techniques, i.e., logistic regression, support vector machine (SVM), k-nearest neighbours (KNN), and recurrent neural network (RNN). The machine learning techniques predict the sentiments of provided reviews in two scenarios, i.e., scenario 1 - negative (-) and positive (+) and scenario 2 - negative (-), neutral (0) and positive (+). In this paper, we have proposed the architecture for predicting the sentiments with better accuracy over other techniques.