Here we present a technique to compute the sentiments of movie review dataset so t hat the overall performance of the model is optimised. This model is certain to train and test the model and find the performance constraints. We first pre - process the dataset followed by feature selection and then we will classify the features to investigate the performance. A textual movie review is important as it reveals strong and weak points of the movie plot and by doing the deeper analysis of a movie review one can tell if movie will meet the expectations of the reviewer. https://www.ijiert.org/paper-details?paper_id=141060