Deteksi Konten Judi Online pada Teks Media Sosial Menggunakan Support Vector Machine dengan Ekstraksi Fitur TF-IDF

Abstract

The rapid growth of social media has made it easier for users to interact and share information. However, social media has also become a medium for spreading negative content, one of which is online gambling promotion. Online gambling content is often distributed through comments on various social media platforms, creating the need for an automated detection method. This study aims to develop a classification model capable of detecting comments containing online gambling content using the Term Frequency-Inverse Document Frequency (TF-IDF) and Support Vector Machine (SVM) methods. The dataset used in this study was obtained from Kaggle and consists of 10,230 Indonesian YouTube comments, comprising 4,209 online gambling comments and 6,021 non-gambling comments. The research stages include data collection, preprocessing consisting of case folding, cleaning, tokenizing, stopword removal, and stemming, feature extraction using TF-IDF, data splitting with an 80:20 ratio, model training using the SVM algorithm, and evaluation using a confusion matrix, accuracy, precision, recall, and F1-score. The results show that the SVM model with a linear kernel achieved excellent classification performance, obtaining a training accuracy of 99.40% and a testing accuracy of 98.19%. In addition, the model achieved a precision of 99%, recall of 97%, and F1-score of 98%. These results indicate that the combination of TF-IDF and SVM is effective for detecting online gambling content in social media comments.