Social Network Analysis of BSI Data Leakage Using Naive Bayes, Support Vector Machine (SVM), and Random Forest Classification Algorithms

This research aims to design a sentiment analysis detection system in the context of the BSI bank digital data hacking case. The main focus of the research is to compare the performance of three different classification algorithms, namely Random Forest, Naive Bayes, and Support Vector Machine (SVM), which were used to analyze sentiment in the BSI bank digital data hacking case. The data collected was 24,000 tweets, with neutral sentiment reaching 83.86%, negative sentiment 8.43%, and positive sentiment 7.71%. The evaluation results show that the Support Vector Machine classification algorithm has the highest accuracy in identifying sentiment in tweet data related to BSI, namely 95.72%. Meanwhile, Naive Bayes has an accuracy of 89.73%, and Random Forest reaches 95.7%. This research provides a deep understanding of sentiment analysis, especially in the context of data leaks in the digital era.