Sentiment Analysis of Mobile Phone Products Reviews Using Classification Algorithms

Abstract

Sentiment analysis or opinion mining is a process of analyzing opinions and emotions to infer the tendencies and impressions shown on the analyzed data and classify them as positive or negative. Sentiment analysis is extremely important because it helps companies and institutions to measure the scope of their customer's satisfaction with a specific product based on reviews in a very fast way. As the manual analysis of these reviews is very difficult because of the increase in the numbers of reviews on products day after day. This paper proposes a sentiment analysis model to classify product reviews as positive, neutral and negative. It applies five popular machine learning classifiers namely: Naive Bayes, Support Vector Machine, Decision Tree, K-Nearest Neighbor and Maximum Entropy with the aim to come up with the most efficient classifier. The dataset used consists of 82,815 reviews about mobile phone products, collected from Kaggle website. In order to evaluate the five classifiers, we used recall, precision, F1-mesaure and accuracy to measure the performance of each algorithm. The results show that Maximum Entropy and Naïve Bayes outperforms the other classifiers in term of accuracy in all experiments. Decision Tree algorithm gave the lowest results across all experiments in terms of accuracy.