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

Spam Detection for Youtube using Bayesian Method

Author(s):

Shishir Sunil Kurhade , Smt.Kashibai Navale College Of Engineering,Vadgaon,Pune; Murtaza Khambaty, Smt.Kashibai Navale College Of Engineering,Vadgaon,Pune; Shreeya Jaiswal, Smt.Kashibai Navale College Of Engineering,Vadgaon,Pune; Susmit Gaikwad, Smt.Kashibai Navale College Of Engineering,Vadgaon,Pune

Keywords:

Data Mining, Web Crawling, Spam Detection, YouTube, Bayesian Analysis

Abstract

In the last few years, social media websites have seen a dramatic growth in the number of users. More and more people are now communicating over the internet using social media websites, thus, these websites are very popular nowadays. Just like any other, YouTube is one popular video streaming social media website. A whooping 1 billion users visit the website every month. But it has become susceptible to different types of unwanted malicious spamming. Currently, YouTube relies on the community to flag videos which they find inappropriate, and it considers mass comments and messages as a part of spamming. The need to identify spam is more elaborate and so it should be done not only using flags and text mining of comments but also considering other attributes related to a video. Here, we have proposed a system capable of identifying spam based on Naïve Bayes Algorithm. The results of Naïve Bayes Algorithm are compared with other data mining algorithms and techniques. Also, ways in which the results generated by the system can be improved are stated.

Other Details

Paper ID: SPDM038
Published in: Volume : 1, Issue : 2
Publication Date: 01/11/2015
Page(s): 29-31

Article Preview




Download Article

Share