Tweet Sentiment Analysis (TSA) for Cloud Providers Using Classification Algorithms and Latent Semantic Analysis

• 作者: Charalampos Apostolopoulos Ioannis Karamitsos Saeed Albarhami
• 来源期刊: 数据分析和信息处理(英文)
• 学科: 工学
• 关键词: AZURE AWS Google CLOUD MACHINE Learning SENTIMENT Analysis Tweets
• 年，卷（期）: 2019,（4）
• 页码范围: 276-294
• 页数: 19页
• 分类号: TP3

摘要

The availability and advancements of cloud computing service models such as IaaS, SaaS, and PaaS;introducing on-demand self-service, auto scaling, easy maintenance, and pay as you go, has dramatically transformed the way organizations design and operate their datacenters. However, some organizations still have many concerns like: security, governance, lack of expertise, and migration. The purpose of this paper is to discuss the cloud computing customers’ opinions, feedbacks, attitudes, and emotions towards cloud computing services using sentiment analysis. The associated aim, is to help people and organizations to understand the benefits and challenges of cloud services from the general public’s perspective view as well as opinions about existing cloud providers, focusing on three main cloud providers: Azure, Amazon Web Services (AWS) and Google Cloud. The methodology used in this paper is based on sentiment analysis applied to the tweets that were extracted from social media platform (Twitter) via its search API. We have extracted a sample of 11,000 tweets and each cloud provider has almost similar proportion of the tweets based on relevant hashtags and keywords. Analysis starts by combining the tweets in order to find the overall polarity about cloud computing, then breaking the tweets to find the specific polarity for each cloud provider. Bing and NRC Lexicons are employed to measure the polarity and emotion of the terms in the tweets. The overall polarity classification of the tweets across all cloud providers shows 68.5% positive and 31.5% negative percentages. More specifically, Azure shows 63.8% positive and 36.2% negative tweets, Google Cloud shows 72.6% positive and 27.4% negative tweets and AWS shows 69.1% positive and 30.9% negative tweets.