High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Detect and Filter Model For Undesired Message Posted on Online Social Network User Walls


Sudiksha Chakre, , Pad. Dr.D.Y. Patil Institute of Engineering and Technology; Namrata Pattewar, Pad. Dr.D.Y. Patil Institute of Engineering and Technology; Harsha Suryawanshi, Pad. Dr.D.Y. Patil Institute of Engineering and Technology; Puja Gaikwad, Pad. Dr.D.Y. Patil Institute of Engineering and Technology


OSNs, Information Filtering, Information Retrieval, Text Classification, Vector Space Model


OSN is the most interactive media to connect with different people over the internet. Some OSN site does not have an ability to control unwanted messages posted on user’s wall. A proposed approach provides a solution to have direct access control for posted messages in terms of several metrics. It gives a review of various technique such as Machine Learning, rule based system. Machine Learning provides different algorithm for text categorization and rule based system helps to customize the filtering criteria. Today OSN’s provide little support to prevent unwanted messages on user walls. For example face book allows users to state who is allowed to insert messages in their walls (i.e) friends, friends of friends, defined group of friends. Filtered wall is used to filter unwanted messages from OSN user walls. We used Machine Learning text categorization technique to automatically categorize each short text messages based on its content. We base the overall short classification strategy on Radial Basis Function Networks (RBFN) for their proven capabilities in acting as soft classifiers in managing noisy data and intrinsically vague classes. We use the neural model RBFN categorizes as Neural and Non-neural FR filtering rules by which it can state what contents should not be displayed on their walls. In addition, the system provides the user defined Blacklists that is mainly used to temporarily prevent to post any kind of message on a user wall.

Other Details

Paper ID: IJSRDV3I1019
Published in: Volume : 3, Issue : 1
Publication Date: 01/04/2015
Page(s): 786-789

Article Preview

Download Article