<![CDATA[The significant increase in social media usage has contributed to the rise in cyberbullying incidents, particularly in the context of multilingual language use. This study aims to conduct sentiment analysis to detect potential cyberbullying content on the X application using a bilingual approach (Indonesian and English) and leveraging the Naive Bayes (NB) and Support Vector Machine (SVM) algorithms. Tweets are collected and processed through a pre-processing stage to extract relevant features for sentiment analysis. Both algorithms are then applied to classify tweets into positive, negative, or neutral categories and identify indications of cyberbullying. The results of the trials indicate that the NB algorithm outperformed SVM, achieving an accuracy rate of 87%. Furthermore, in identifying cyberbullying patterns in bilingual text, NB reached the highest accuracy rate for the Indonesian language at 87%. These findings suggest that this study can serve as a reference for developing more accurate and responsive cyberbullying detection systems on bilingual social media platforms.]]>
Copyrights © 2025
