Implementation Of Random Forest Algorithm On Youtube Comment Sentiment Analysis Regarding Global Conflict Issues For Early Detection Of Psychological Threats

Rekayasa Keamanan Siber

Abstract

The spread of provocative narratives on social media during global tensions poses a psychological threat to national stability. This study aims to classify public sentiment regarding World War 3 issues using the Random Forest algorithm to support cyber defense readiness. Data was collected via YouTube API focusing on relevant news channels, preprocessed using TF-IDF, and classified into positive, negative, and neutral categories. The Random Forest model was configured with 100 estimators and evaluated using 5-fold cross-validation. The results show that Random Forest achieved an accuracy of [Isi % Accuracy] with higher precision compared to other methods. Negative sentiment dominated by fear and uncertainty indicates potential vulnerability to psychological operations. It is concluded that this model can serve as an early warning system for monitoring information warfare threats.