Abstract

As the use of On-line Social Networks (OSNs) rapidly increases, today there is need to provide users with the facility of controlling the messages posted on their private wall to avoid some unwanted content to be displayed. Up till now such requirement is shortly fulfilled by OSNs. But for user convenience, in this paper, a system which we propose is basically to provide users a classification mechanism to avoid useless data. Information filtering technique can also be used for some different and more sensitive, purpose as well. So, mainly our propose system allowing OSN users to have a direct control on the messages posted on their walls. This is possible to achieve through an experimental evaluation an automated system known as Filtered Wall (FW) which has capability to filter unwanted messages from OSN user walls on the basis of both message content and the message creator relationships and characteristics of it. We also insert the neural model in the hierarchical form of two level classification strategies. Besides these classification facilities, our system also provides a powerful rule layer enhancing a flexible language to specify Filtering Rules (FRs), through which users can mention, what contents they do not want to be displayed on their walls and We exploit automatically assign Machine Learning (ML) text categorization techniques for each short text message a set of categories based on its content. This strategy is based on Radial Basis Function Networks (RBFN), managing noisy data and intrinsically vague classes. More- over, the flexibility of the system in terms of filtering options is enhanced through the management of Black lists (BLs).

Authors and Affiliations