Spam Detection in Connected Networks Using Particle Swarm and Genetic Algorithm Optimization: Youtube as a Case study
Amel Ali Alhussan *1, Hassan K. Ibrahim Al-Mahdawi2, Ammar Kadi3
1Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
2Electronic and Computer Center, University of Diyala, Baqubah MJJ2+R9G, Iraq
3 Department of Food and Biotechnology, South Ural State University; pr. Lenina 76, Chelyabinsk, 454080 Russia
Emails: aaalhussan@pnu.edu.sa; hssnkd@gmail.com; ammarka89@gmail.com
Abstract
Although there are many networks security tools, both wire and wireless connected networks are still suffering from many types of attacks. YouTube's meteoric rise to prominence as a social platform speaks for itself. The sheer volume of comments on YouTube has made it an ideal medium for spammers to spread their malicious software. Phishing attacks, in which anyone who clicks on a bad link might be a victim, have contributed to this problem. Classification systems may be used to examine spam for its unique characteristics and identify it. This is why it is suggested that YouTube already has built-in mechanisms for identifying spam. A YouTube Spam detection framework was designed with the five stages of data collection, pre-processing, features extraction, classification, and detection, allowing for the execution of the tests. To analyze and validate each stage of the YouTube detection methodology presented in this study, two metaheuristic optimization methods are employed to optimize the parameters of a new voting ensemble classifier. These methods are the particle swarm optimization (PSO) and the Genetic Algorithm (GA). The ensemble model is based on three classifiers: neural. Results indicate that the proposed approach is accurate. In addition, statistical analysis is performed to emphasize the superiority and effectiveness of the proposed methodology.
Keywords: Connected Networks; Spam detection; Voting ensemble; Neural network; Support vector machine; Decision tree.