Comparison of Supervised Machine Learning Algorithms for Spam E-Mail Filtering
Journal: International Journal for Scientific Research and Development | IJSRD (Vol.3, No. 11)Publication Date: 2016-02-01
Authors : Nidhi;
Page : 752-754
Keywords : Spam; Ham; Training; Testing; Filtering; Machine Learning; Classification;
Abstract
Spam is an Unsolicited Commercial Email(UCE).It involves sending messages by email to numerous recipients at the same time (Mass Emailing).Spam mails are used for spreading virus or malicious code, for fraud in banking, for phishing, and for advertising. So it can cause serious problem for internet users such as loading traffic on the network, wasting searching time of user and energy of the user, and wastage of network bandwidth etc.To avoid spam/irrelevant mails we need effective spam filtering methods. This Paper compares and discusses performance measures of certain categories of supervised machine learning techniques such as Naive Bayesian and k-NN algorithms and also proposes a better Na�¯ve Bayesian approach.
Other Latest Articles
- Characterisation of WTO (Waste Transformer Oil) & Diesel by Fourier transform infrared spectroscopy & Effect of Additives on Properties of WTO-Diesel Blends
- Performance Evaluation of Tractor Mounted Hydraulic Elevator
- Automatic Pallet Carrier for Small Workshop
- A Study Of Chemical Constitution Of Lignin Of Leucaena Leuccephala
- Comparison of Different Techniques for Distribution System Load Flow Analysis-A Review
Last modified: 2016-02-08 16:54:48