期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2021
卷号：99
期号：22
语种：English
出版社：Journal of Theoretical and Applied
摘要：Sentiment analysis also called opinion mining, is the field of study that analyses people�s opinion, sentiment, evaluations, appraisals, attitudes and emotions towards entities such us services, organizations, individuals, issues, events, topics and products. The fast evolution of Internet-based applications like websites, social networks, and blogs, leads people to generate enormous heaps of opinions and reviews about products, services, and day-to-day activities. Sentiment analysis poses as a powerful tool for businesses, governments, and researchers to extract and analyze public mood and views, gain business insight, and make better decisions.There are many approaches to classify the sentiment, approaches based on machine learning or lexicon-based approach. In this article we will discuss the different approaches of sentiment analysis, and we will compare the performance of the different machine learning algorithms. In this comparative study we will use the na�ve Bayes, Support vector Machine, the Decision Tree and the Logistic regression algorithms to analyze the sentiments in amazon�s reviews data. The main objective is to analyze the large number of reviews expressed in amazons in order to deduce the different feelings expressed in it, positive, negative or neutral.The main goal of this work is to achieve the best result of sentiment analysis. So, to analyze and classify the data we will start by preprocessing the data then the features extraction after that the sentiment classification using the machine learning algorithms and finally the evaluation of the algorithms, using Spark and Scala language for implementing the algorithms. The final results show that the SVM classifier achieved 100% accuracy, Naive Bayes classifier achieved 95% accuracy, the Logistic regression 97% and the Decision Tree classifier achieved 75% accuracy.
