ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Filtered Wall: An Automated System to Filter Unwanted Messages from OSN User Walls?

Journal: International Journal of Computer Science and Mobile Computing - IJCSMC (Vol.3, No. 2)

Publication Date:

Authors : ;

Page : 767-772

Keywords : Online social networks; Filtered Wall; Blacklists; Machine Learning text categorization;

Source : Downloadexternal Find it from : Google Scholarexternal


Now days On-line Social Networks (OSNs) are one of the most popular interactive medium to communicate, share, and disseminate a considerable amount of human life information. This project represents a system enforcing filtering of unwanted messages coming from the user based on its content. Our system gives ability to OSN users to have a direct control on the messages posted on their walls. Up to now, OSNs provide little support to prevent unwanted messages on user walls. There is no content-based preferences are supported and therefore it is not possible to prevent unwanted messages, such as political or vulgar ones, no matter of the user who posts them. Providing this service is not only a matter of using previously defined web content mining techniques for a different application, rather it requires to design ad hoc classification strategies. This is because wall messages are constituted by short text for which traditional classification methods have serious limitations since short texts do not provide sufficient word occurrences. One fundamental issue in this system is blocking of user for lifetime. We overcome this Problem by using Proposed System; In this paper, we propose a system that performs blocking of user for particular time limit and also send notification, E-Mail to that who has posted unwanted message on wall. Along with that we are using Self Organizing Neural Network (SOINN) with Redial Based Function (RBF) for classification of text. In this we use the back propagation technique of neural network (i. e. Using previous knowledge of user messages we take proper action).

Last modified: 2014-03-03 21:26:37