Sentimentalizer: Docker container utility over Cloud

Abstract

In this computer era, the most interesting thing is to determine the human opinion using machines. Humans use opinions for conveying their response on a host of things to others. With the increasing popularity and availability of enriching opinion mediums such as personal blogs, forum discussions, online review sites, and micro blogging sites like Twitter, there are new challenges and opportunities for using this information to understand and analyze the sentiments of others. However, web texts usually seem noisy and represent significant issues at the lexical as well as the syntactic level. In this paper, lightweight Docker container is employed over cloud as a utility for sentiment analysis using the four popular classification approaches. It analyzes the reviewer's comment on a product across multiple websites. The analyzed information can be used as a recommendation for the product to a customer. The evaluation process on NLTK benchmark movie review dataset is performed with accuracy, computational cost and resources utilization. The computational analysis shows that our proposed approach meets the requirements of the real time applications over Cloud.