A System to Clarify Unwanted Messages from OSN User Surface

Aarti Supe, R. N. Phursule

Abstract: Today Online Social Networks (OSNs) are one of the most wanted and popular social networks where users can share, exchange and communicate with the large amount of information to each other. One basic issue in these OSNs is to give users a protected private space from the undesirable and unwanted messages displayed. So the main goal of the present work is to propose and experimentally evaluate Filtered Wall (FW) which is an automated system can filter noisy messages from OSN user space. This is possible through a flexible rule-based system that allows users to customize the filtering options to be used to their surfaces and a Machine Learning (ML) depended soft classifier involuntarily labeling messages in support of content-based filtering.

Keywords: Online social network (OSN), Short text classification, Message Filtering, RBNF, Blacklists, CBMF.