Sentiment Analysis on Movie Reviews

Introduction Sentiment Analysis, the process defined as “aims to determine the attitude of a speaker or a writer with respect to some topic” in Wikipedia, has recently become an active research topic, partly due to its potential use in a wide spectrum of applications ranging from “American idol” popularity analysis to product user satisfaction analysis. With the rapid growth of online information, a large amount of data is at our fingertips for this kind of analysis. However, the sheer volume of information was a daunting challenge itself. To separate relevant information from the irrelevant, and to gain knowledge from this unprecedented deluge of data, automatic algorithm is essential. In this project, we explored the use of various supervised machine learning algorithms in learning sentiment classifier and tested the effectiveness of different feature selection algorithms in improving those classifiers.