Exploiting latent content based features for the detection of static SMS spams. Issue 1 (2014)

• Record Type: Journal Article
• Authors: Karami, Amir; Zhou, Lina
• Is Part Of: Proceedings of the annual meeting of the American Society for Information Science and Technology. Volume 51:Issue 1(2014)
• Page Start: 1
• Page End: 4
• Publication Date: 2014
• Subjects: Spam Detection -- SMS -- Classification -- Content Features -- LDA; Information science -- Congresses; Electronic information resources -- Congresses; 020
• DOI: 10.1002/meet.2014.14505101157
• Languages: English
• ISSNs: 1936-1734

Abstract

ABSTRACT: As the use of mobile phones grows, spams are becoming increasingly common in mobile communication such as SMS, calling for research on SMS spam detection. Existing detection techniques for SMS spams have been mostly adapted from those developed for other contexts such as emails and the web without taking into account some unique characteristics of SMS. Additionally, spamming tactics is constantly evolving, making existing methods for spam detection less effective. In this research, we propose to exploit latent content based features for the detection of static SMS spams. The efficacy of the proposed features is empirically validated using multiple classification methods. The results demonstrate that the proposed features significantly improve the performance of SMS spam detection.