A Cloud Based Sentiment Analysis through Logistic Regression in AWS Platform

Abstract

The use of Amazon Web Services is growing rapidly as more users are adopting the technology. It has various functionalities that can be used by large corporates and individuals as well. Sentiment analysis is used to build an intelligent system that can study the opinions of the people and help to classify those related emotions. In this research work, sentiment analysis is performed on the AWS Elastic Compute Cloud (EC2) through Twitter data. The data is managed to the EC2 by using elastic load balancing. The collected data is subjected to preprocessing approaches to clean the data, and then machine learning-based logistic regression is employed to categorize the sentiments into positive and negative sentiments. High accuracy of 94.17% is obtained through the proposed machine learning model which is higher than the other models that are developed using the existing algorithms.