Feature Based Sentimental Analysis for Prediction of Mobile Reviews

In order to achieve this the machine learning model would have to accomplish various tasks such as word segmentation stop-words extraction of features and finding similar products other users have purchased etc. In this project we take the example of mobile recommendation system and we tried to categorize the mobile reviews as positive or negative using sentiment analysis and have built a recommender system using an improved item based collaborative filtering based on the sentiment of users which can suggest mobiles that a user may like based on the list of mobiles he has already watched.