As recently seen in Facebook the posts are not classi?ed and also automatic account banning is not possible. Thus we aim to focuses on the classi?cation of facebook news feeds. We classify the users news feeds into various categories using classi?ers to provide a better representation of data on user wall. News feeds collected from facebook are dynamically classi?ed into various classes such as historical entertainment political educational etc. Posts or updates from pages which are liked by the users are grouped as liked pages posts. Posts from friends are tagged as friend posts and those regarding the events occurring in their lives are said to be life event posts and the rest are tagged as entertainment posts. This helps users to ?nd important news feeds from live news feeds. Sentiments are important part of the process as they depict the opinions and expressions of the user. Hence detecting the sentiments of users from the different classi?cation also becomes an essential task. We also propose a system for automatic detection of illegal posts and categorize based on sentiment URLAPI. And also some illegal posts must be checked and account should be blocked and if user exceeds such limits then account should be banned. By using graph we can show that how many accounts banned.
SVM-naïve bayes-random forest-DNN-Multinomial Logistic Regression