Year: 2021
Type: article
Abstract: With the growth of mobile phones, short message service (SMS) became an essential text communication service. However, the low cost and ease use of SMS led to an increase in SMS Spam. In this paper, the characteristics of SMS spam has studied and a set of features has introduced to get rid of SMS spam. In addition, the problem of SMS spam detection was addressed as a clustering analysis that requires a metaheuristic algorithm to find the clustering structures. Three differential evolution variants viz DE/rand/1, jDE/rand/1, jDE/best/1, are adopted for solving the SMS spam problem. Experimental results illustrate that the jDE/best/1 produces best results over other variants in terms of accuracy, false-positive rate and false-negative rate. Moreover, it surpasses the baseline methods.
Author: Sarab M. Hameed
Institution: University of Baghdad
Language: English
Topic: Spam and Phishing Detection
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W3045863345
