SMS spam filtering based on text classification and expert system

Author

Bozan, Yavuz Selim ; Coban, Onder ; Ozyer, Gulsah Tumuklu ; Ozyer, Baris

Author_Institution

Bilgisayar Muhendisligi Bolumu, Ataturk Univ., Erzurum, Turkey

fYear

2015

fDate

16-19 May 2015

Firstpage

2345

Lastpage

2348

Abstract

Even though short message service(SMS) is gradually being replaced by social network sites´ messaging systems, it still is one of the most widely used communication systems. For reasons such as well established e-mail filter systems, cheap SMS bundles and ineffective spam solutions for message services, SMS is one of the services which is widely used by advertising companies. In this study, expert system and data classification methods are proposed for SMS spam problem and a prototype software for Jelly Bean version of Android operating system. SVM, bayesian classification and k-NN classification methods applied and 98.61%, 97.55% and 93.35% successful results were obtained.

Keywords

Android (operating system); Bayes methods; e-mail filters; electronic messaging; expert systems; information filtering; pattern classification; social networking (online); support vector machines; text analysis; unsolicited e-mail; Android operating system; Bayesian classification; Jelly Bean version; SMS bundles; SMS spam filtering; SMS spam problem; SVM; advertising companies; communication systems; data classification methods; e-mail filter systems; expert system; k-NN classification; message services; prototype software; short message service; social network site messaging systems; text classification; Androids; Filtering; Humanoid robots; Mobile communication; Niobium; Support vector machines; Unsolicited electronic mail; Bayes; SVM; Spam SMS; android; expert systems; k-NN; mobile system software;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Communications Applications Conference (SIU), 2015 23th

Conference_Location

Malatya

Type

conf

DOI

10.1109/SIU.2015.7130350

Filename

7130350