Comparative evaluation of deep learning and machine learning techniques for sentiment analysis of electronic product review data

Abstract

The primary thoughts, perceptions, attitudes, feedback, and even emotions expressed by people on social networking and e-commerce sites are the primary focus of sentiment analysis also referred to as opinion mining. It provides meaningful information to various stakeholders and customers in influencing their next move. However, the biggest challenge is the extraction of relevant information from the tremendous data. Machine learning and deep learning techniques have obtained remarkable success in exemplifying and classifying information. Machine learning works with the binary classification of information, whereas deep learning provides automatic feature detection. A study was carried out to extract the relevant information from the Amazon reviews dataset of electronics products. The Naïve Bayes, support vector machine, decision tree, convolution neural network, long short term memory, recursive neural networks, and recurrent neural networks were used on the dataset after applying different data preprocessing. To evaluate the performance of various machine learning and deep learning techniques, frameworks, F1 score, precision, recall as well as, accuracy was used. The results suggest that deep learning techniques have outperformed the machine learning techniques, and RNN shows the highest accuracy among all the techniques.

Keywords

• sentiment analysis
• deep learning
• machine learning
• nb
• svm
• lstm
• rnn
• cnn
• recnn