Identifikasi Phising pada Pesan Teks Menggunakan Algoritma Support Vector Machine dengan Ensembled Bagging

Abstract

Phishing is a type of social media crime that steals personal data from individuals or industries. Phishing can be delivered in various forms, one of which is through text messages, known as smishing. Smishing contains text messages that include email addresses, phone numbers, or website links that attract the recipient without realizing the crime. Such crimes can harm the recipient financially or compromise data security. However, identifying smishing is still challenging because these messages must be identified manually, a process that takes a long time. Therefore, an approach is needed to detect phishing in text messages quickly and more accurately. This study aims to identify phishing in text messages using the Support Vector Machine (SVM) algorithm with Ensembled Bagging. The methodology includes collecting 1600 phishing and non-phishing texts obtained from previous research and the researcher's message box, then preprocessing the data through cleaning, tokenization, stopwords elimination, and stemming. The data is then divided into training and testing sets. The SVM algorithm is used as the base model and optimized with Ensembled Bagging to improve identification accuracy. The results show that the proposed approach successfully identifies phishing with an accuracy of 95.2%, proving that the combination of SVM and Ensembled Bagging is effective in processing text message data for phishing identification.