Anzeige
Erschienen in:
2016 | OriginalPaper | Buchkapitel
Comparative Study of Classification Algorithms for Spam Email Detection
verfasst von : Aakanksha Sharaff, Naresh Kumar Nagwani, Abhishek Dhadse
Erschienen in: Emerging Research in Computing, Information, Communication and Applications
Verlag: Springer India
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Spam in emails has become a major issue. Spam messages consume space, network bandwidth and are of no use to the receiver. It is very difficult to filter spam as spammers try to tackle the processes carried out by the filtering mechanism. Various classification algorithms are used to classify a mail as spam or non-spam (ham). The present paper compares and discusses the effectiveness of four machine learning classification algorithms, belonging to different categories (Probabilistic, Decision Tree, Vector Machines and Lazy Algorithms) on the basis of various performance measures, using WEKA, a data mining tool to analyze different algorithms. Enron dataset is taken in a processed form from Athens University of Economics and Business and it is found that J48 and BayesNet algorithms perform better than SVM.