Emotions are an important part of human life. It creates direct effect when the gestures of people are visible to the audience, but it is unclear when only texts are used rather than used in combination with gestures and facial expression. As the wide use of internet and mobile, text data has become the main source of communication in several social networking sites. One way of making such textual based interaction more interactive is to make a system that can recognize the sentimental purpose present behind the text. Now a days several researches are ongoing to make computer and human interaction as effective as it can detect the sentimental state of a person.  This paper focuses on studying different work done in the area of sentiment analysis through text mining and provides a review that covers the best method and techniques used based on the previous experimental result.