Thanks to the advent of numerous social networking platforms, anyone may now easily create, express, and share thoughts, feelings, opinions, and ideas with millions of people globally. People express their ideas through tweets on Twitter, one of the most well-known microblogging sites, which makes it a valuable resource for emotive research. A tweet’s content is classified based on whether it includes factual facts or opinions. A detailed examination is required to ascertain the person’s thoughts on the tweets they wrote. Based on the message’s polarity, sentiment analysis divides it into negative, positive, and neutral categories. In this research, we offer a support vector machine-based approach for sentiment analysis on social media data. The support vector machine can be used to find the separated hyperplane that maximizes margin for each of the classes. Based on simulation results, our suggested approach outperforms the current approaches in terms of accuracy.