Developing an Intelligent System with Deep Learning Algorithms for Sentiment Analysis of E-Commerce Product Reviews

Most consumers rely on online reviews when deciding to purchase e-commerce services or products. Unfortunately, the main problem of these reviews, which is not completely tackled, is the existence of deceptive reviews. The novelty of the proposed system is the application of opinion mining on consumers' reviews to help businesses and organizations continually improve their market strategies and obtain an in-depth analysis of the consumers' opinions regarding their products and brands. In this paper, the long short-term memory (LSTM) and deep learning convolutional neural network integrated with LSTM (CNN-LSTM) models were used for sentiment analysis of reviews in the e-commerce domain. The system was tested and evaluated by using real-time data that included reviews of cameras, laptops, mobile phones, tablets, televisions, and video surveillance products from the Amazon website. Data preprocessing steps, such as lowercase processing, stopword removal, punctuation removal, and tokenization, were used for data cleaning. The clean data were processed with the LSTM and CNN-LSTM models for the detection and classification of the consumers' sentiment into positive or negative. The LSTM and CNN-LSTM algorithms achieved an accuracy of 94% and 91%, respectively. We conclude that the deep learning techniques applied here provide optimal results for the classification of the customers' sentiment toward the products.