Improving Probabilistic Spam Detector using Features Subset Selection |
Author(s): |
| Mayur Saini , Modern Institute Of Engineering and Technology, Mohri, Haryana, India; Bhumika Garg, Assistant Professor (Modern Institute Of Engineering and Technology, Mohri) |
Keywords: |
| Web Spam, Naïve Bayes Classifier, Features Subset Selection (FSS), Probability Estimation, Spam Detector |
Abstract |
|
Basically Spam is any spontaneous thing or unnecessary emails as well as mainly a promotional material which are occurred in our delicate account. Spam like an Unsolicited Commercial Email, Unsolicited Bulk Email and Unsolicited Automated Email which have been sent out without request or consent of the recipients by many parties. Spam imposes countless prices issues from easy web capacity, computational issues and storage costs issues to user productivity. Most of the Spam Detection Algorithm utilizes the simplicity of Naïve Bayes Classifier. But we have modified Naive Bayes Classifier using Features Subset Selection (FSS) improvements in such a way that web spam and false alarm get minimize. These algorithms are usually fast and large enterprises such as Google, Microsoft and other major Email Provider utilize these algorithm |
Other Details |
|
Paper ID: IJSRDV3I70112 Published in: Volume : 3, Issue : 7 Publication Date: 01/10/2015 Page(s): 144-146 |
Article Preview |
|
|
|
|
