Spam Filtering based on Naïve Bayesian with Information Gain and Ant Colony System | ||
| Iraqi Journal of Science | ||
| Article 1, Volume 57, Issue 1, January 2016, Pages 719-727 | ||
| Authors | ||
| Huda Adil Abd Algafore; Soukaena Hassan Hashem | ||
| Abstract | ||
| This research introduces a proposed hybrid Spam Filtering System (SFS) which consists of Ant Colony System (ACS), information gain (IG) and Naïve Bayesian (NB). The aim of the proposed hybrid spam filtering is to classify the e-mails with high accuracy. The hybrid spam filtering consists of three consequence stages. In the first stage, the information gain (IG) for each attributes (i.e. weight for each feature) is computed. Then, the Ant Colony System algorithm selects the best features that the most intrinsic correlated attributes in classification. Finally, the third stage is dedicated to classify the e-mail using Naïve Bayesian (NB) algorithm. The experiment is conducted on spambase dataset. The result shows that the accuracy of NB with IG-ACS is better than NB with IG only | ||
| Keywords | ||
| Ant Colony System; Feature Selection; Information Gain; ve Bayesian and Spam Filtering System | ||
|
Statistics Article View: 178 PDF Download: 70 |
||