Digital info out there on the net is increasing day by day. As a result of this, the demand for tools that facilitate individuals to find and analyzing of these resources also are growing in variety. Text Classification, particularly, has been terribly helpful in managing the information. Text Classification is that the method of assignment language text to 1 or a lot of classes supported the content. Its several necessary applications within the globe. As an example, finding the sentiment of the reviews, denote by people on restaurants, movies and different such things area unit all applications of Text Classification. During this project, the focus has been ordered on Sentiment Analysis that identifies the opinions expressed in a very piece of text. It involves categorizing opinions in text into classes like 'positive' or 'negative'. Existing works in Sentiment Analysis centered on decisive the polarity (Positive or negative) of a sentence. This comes below binary classification, which suggests classifying the given set of components into 2 teams. The aim of this analysis is to handle a unique approach for Sentiment Analysis known as Multi category Sentiment Classification. During this approach the sentences area unit classified below multiple sentiment categories like positive, negative, neutral then on. Classifiers area unit engineered on the prognostic Model, that consists of multiple phases. Analyses of various sets of options on the info set, like stemmers, n-grams, tf-idf then on, are thought of for classification of the info. Totally different classification models like Bayesian Classifier, Random Forest and SGD classifier area unit taken into thought for classifying the info and their results area unit compared. Frameworks like woodhen, Apache driver and sickest area unit used for building the classifiers