Abstract

Machine learning and artificial intelligence-based sentiment analysis are crucial for companies to automatically predict whether the customers are happy with their products. In this paper, a deep learning model is built to analyze thousands of reviews of Amazon Alexa to predict customer sentiment. The proposed model can be directly applied to any company that has an online presence to automatically detect customer sentiment from their reviews. The objective of this research work is to propose a suitable method for analyzing the users’ reviews of Amazon Echo and categorizing them into positive or negative reviews. In this research work, a dataset containing reviews of 3150 users has been used. Initially, a word cloud of positive and negative reviews has been plotted that gave a lot of insight from the text data. After that, a deep learning model using a multinomial naïve Bayesian classifier has been built and trained by using 80% of the dataset, and then the remaining 20% of the dataset has been used for testing the model. The proposed model gives 93% accuracy. The proposed model has also been compared with four models used in the same domain, and it outperformed three of them.