Now a day Online Social Networks (OSNs) have become more popular among the internet users. But it has one major problem i.e. to prevent unwanted messages posted on user's personal space. OSNs provide very little support to this requirement. So we have proposed a system which makes the classification of messages and content based filtering from OSN user walls.This system permits OSN users to have a direct control on the messages posted on their walls by using a flexible rule-based system, that permit users to customize the filtering criteria to be put to their walls and a Machine Learning-based soft classifier that automatically classify and labels the messages in endure of content based filtering.

No abstract