Sentiment Analysis of Twitter Posts using Machine Learning Algorithms

Sentiment Analysis refers to the use of Natural Language Processing to determine the attitude of a speaker, writer,or other subject with respect to some topic or the overall contextual polarity to a document, interaction, or event. Sentiment Analysis can be applied to domains such as marketing, crowd surveillance, customer service and psychology. In recent years, there has been a tremendous increase in the rate at which data is generated by users on social media platforms such as Twitter. This user-generated data is a valuable source for mining public's opinion and hence opens up several opportunities for Sentiment Analysis. This paper focuses on using machine learning techniques for sentiment analysis of the posts on the micro blogging website - Twitter. Four major machine learning techniques have been used, namely-Decision Tree Classifier, Logistic Regression, Support Vector Machine and Neural Network. The results are analyzed and the advantages of different techniques in comparison to others have been discussed.