Sentiment analysis on movie reviews: A comparative study of machine learning algorithms and open source technologies

Abstract

Social Networks such as Facebook, Twitter, Linked In etc... are rich in opinion data and thus Sentiment Analysis has gained a great attention due to the abundance of this ever growing opinion data. In this research paper our target set is movie reviews. There are diverge range of mechanisms to express their data which may be either subjective, objective or a mixture of both. Besides the data collected from World Wide Web consists of lot of noisy data. It is very much true that we are going to apply some pre-processing techniques and compare the accuracy using Machine Learning algorithm Naiüve Bayes Classifier. With ever growing demand to mine the Big Data the open source software technologies such as Hadoop using map reducing paradigm has gained a lot of pragmatic importance. This paper illustrates a comparitive study of sentiment analysis of movie reviews using Naiüve Bayes Classifier and Apache Hadoop in order to calculate the performance of the algorithms and show that Map Reduce paradigm of Apache Hadoop performed better than Naiüve Bayes Classifier.