Spam Classification Using Machine Learning Techniques - Sinespam
Year: 2010
Type: dissertation
Abstract: Most e-mail readers spend a non-trivial amount of time regularly deleting junk e-mail (spam)\nmessages, even as an expanding volume of such e-mail occupies server storage space and\nconsumes network bandwidth. An ongoing challenge, therefore, rests within the development\nand refinement of automatic classifiers that can distinguish legitimate e-mail from spam. Some\npublished studies have examined spam detectors using Naïve Bayesian approaches and large\nfeature sets of binary attributes that determine the existence of common keywords in spam,\nand many commercial applications also use Naïve Bayesian techniques.\nSpammers recognize these attempts to prevent their messages and have developed tactics to\ncircumvent these filters, but these evasive tactics are themselves patterns that human readers\ncan often identify quickly. This work had the objectives of developing an alternative approach\nusing a neural network (NN) classifier brained on a corpus of e-mail messages from several\nusers. The features selection used in this work is one of the major improvements, because the\nfeature set uses descriptive characteristics of words and messages similar to those that a\nhuman reader would use to identify spam, and the model to select the best feature set, was\nbased on forward feature selection. Another objective in this work was to improve the spam\ndetection near 95% of accuracy using Artificial Neural Networks; actually nobody has reached\nmore than 89% of accuracy using ANN.
Author: José Norte Sosa
Language: English
Topic: Spam and Phishing Detection
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2129744133
