Analisis Sentiment Cyberbullying pada media Youtube menggunakan Algoritma Naïve Bayes

Muhammad Rayhan Elfansyah (Universitas Muhammadiyah Kalimantan Timur)
Muhammad Reifin Perdana (Universitas Muhammadiyah Kalimantan Timur)
Ikhsan Nuttakwa Takbirata Ihram Nabawi (Universitas Muhammadiyah Kalimantan Timur)
Rudiman Rudiman (Universitas Muhammadiyah Kalimantan Timur)

KOMPUTEK
Vol 8, No 1 (2024): April

This research focuses on analyzing cyberbullying sentiment on YouTube using the Naive Bayes algorithm. This study involved data collection and data pre-processing techniques to analyze comments related to Manchester United. The Orange Data Mining application is used for data modeling and analysis. The research methodology and sentiment analysis using Naive Bayes are explained in detail. Data pre-processing includes steps such as removing URLs, tokenization, filtering, and normalization. Analysis uses Naïve Bayes which produces 81% accuracy, 79% precision and 81% recall. The process includes dividing the data into training data and testing data, and the results can be visualized using a confusion matrix. The references include various studies on sentiment analysis using different methods and platforms.