Abstract
The right to speak is guaranteed by the First Amendment to the U.S. Constitution that includes the right to criticize others, and share opinion, comment on any matter. Comments on Social Media display people's political views related to specific racial, ethnic and religious minorities. People strong beliefs and views on any public interest can be determined by their comments on Social Media. This paper investigates and predicts user's views on sensitive and controversial topics such as racism and discrimination, using Twitter as a micro-blogging site. The process includes sentiment analysis and machine learning methods such as Named Entity Recognition (NER) and Polarity algorithm. Due to the unstructured nature of comments and the inaccuracy of the sentiment analysis a preprocessing routine must be developed prior to determining the sentiment. The sentiment Index can help to determine about what content people like or which content has the most sensitive issue.