A twitter sentiment analysis for cloud providers: A case study of Azure vs. AWS

Abstract

The rapid revolution of Social Network Sites (SNS) around the globe is presenting wide range of data that can be used in studies of sentiment analysis about certain products, brands, services… etc. In addition, cloud computing fields had been one of the most interesting fields in research studies. In this paper, we used the sentiment analysis of top leading cloud service providers namely; Amazon and Microsoft Azure to analyse their customers' opinions and reviews. To do that, two datasets are extracted which are consisting of tweets that had either organizations' names or cloud names. We study, and analyze the way customers think about them. In this regard, many organizations tend to find out what do customers think or tweet about their products in order to effectively plan marketing campaigns and try to gain the positive impact of Word-of-Mouth. Results are analyzed and explained in details in term of polarity and emotions classifications to show the impact of sentiment analysis to support organizations decisions. We can note from the emotions classification results that, “joy” category is better for Microsoft Azure comparing to Amazon, The “sadness” percentage is larger for Amazon comparing to Microsoft Azure. Furthermore, we can note from the polarity classification that Microsoft Azure has 65% positive tweets compared 45% for Amazon. In addition, the results show that Amazon has 50% negative polarity compared 25% for Microsoft Azure.