KLASIFIKASI AKUN PALSU PADA MEDIA SOSIAL TWITTER DENGAN KOMPARASI MODEL KERNEL SUPPORT VECTOR MACHINE

Danang Dwi Apriansyah Balany, NIM.: 20206051010 (2024) KLASIFIKASI AKUN PALSU PADA MEDIA SOSIAL TWITTER DENGAN KOMPARASI MODEL KERNEL SUPPORT VECTOR MACHINE. Masters thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (KLASIFIKASI AKUN PALSU PADA MEDIA SOSIAL TWITTER DENGAN KOMPARASI MODEL KERNEL SUPPORT VECTOR MACHINE) 20206051010_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (1MB) | Preview
	Text (KLASIFIKASI AKUN PALSU PADA MEDIA SOSIAL TWITTER DENGAN KOMPARASI MODEL KERNEL SUPPORT VECTOR MACHINE) 20206051010_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

The rapid advancements in information technology and the internet worldwide, including in Indonesia, have transformed how people communicate, interact, and share information. Online social media has been a significant component of this change, particularly in recent years. However, its usage also poses challenges, including privacy issues, the spread of false information, and unethical behavior. One serious issue that has emerged is the presence of fake accounts on social media platforms like Twitter. These fake accounts can threaten cybersecurity and disseminate false information, being used for fraud, unauthorized data acquisition, and other malicious activities. Therefore, detecting and identifying fake accounts is crucial. Machine learning techniques, especially Support Vector Machine (SVM), have proven effective in classifying and detecting fake accounts. This study aims to develop a method for detecting fake accounts using SVM with available kernels, focusing on its application on the Twitter social media platform. The study will investigate relevant features such as username type, user status, and posting patterns. The expected outcome of this research is to enhance the security and integrity of online platforms and help users identify fake accounts more effectively. This study's dataset type and the existing attribute features significantly influence the model.

Share this knowledge with your friends :

Actions (login required)

View Item