Sentiment Analysis of #Saverafah Hashtag on TikTok Using Naive Bayes and Decision Tree Methods

Social media facilitates user communication, both in positive, negative and neutral aspects. One of the popular platforms today is Tiktok, where users can create short videos and interact through comments or private messages, as well as follow the latest news, including the major conflict between Palestine and Israel that has been going on since 1948. In this war, many Palestinian civilians, including children and the elderly, became victims, and are currently trying to flee to Rafah to seek protection. This study aims to analyze public sentiment towards the news of Palestinian refugees heading to Rafah, using two classification methods: Naive Bayes and Decision Tree. Before classification, the data goes through a preprocessing process and TF-IDF weighting, and the two methods are compared to determine the best accuracy. The results showed that the Naive Bayes Multinomial method with the application of SMOTE produced an accuracy of 85.43%, a precision of 86.22%, a recall of 85.43%, and an f1-score of 85.53%. Meanwhile, the Decision Tree C4.5 method with the application of SMOTE produced an accuracy of 94.23%, a precision of 94.58%, a recall of 94.23%, and an f1-score of 94.22%. Based on the evaluation results, the best method for sentiment analysis of the hashtag #SaveRafah is Decision Tree C4.5.