In today's age of technology, the whole world is in a state of rapid change, and as Internet use is worldwide, it is becoming an essential requirement for everyone. Social media on the internet is getting a lot of attention these days. Many people are using social networking applications to voice their opinions on everyday issues, and different ideas of individuals on various topics are expressed and constantly disseminated via numerous social media outlets. It's no secret that social media is one of the largest sources of unstructured data and analyzing this data and extracting meaning from it is a tedious task. In this paper we have not only explored the various machine learning algorithms which may be applied for the sentiment analysis but we have proposed a LSTM based model for sentiment analysis. The experimental results show that LSTM has the highest accuracy among all the models.