Sentiment Analysis of Lau Berte Waterfall Using the Naïve Bayes Algorithm

Abstract

Social media platforms have become important sources of public opinion, allowing users to share experiences and perceptions regarding tourist destinations. One of the platforms widely used for this purpose is TikTok, where visitors frequently express their opinions through comments on video content. This study aims to implement the Naïve Bayes algorithm for sentiment analysis of TikTok comments related to Lau Berte Waterfall and evaluate its performance through a Streamlit-based web application. A total of 634 comments were collected and processed through several text preprocessing stages, including case folding, cleaning, normalization, tokenization, stopword removal, and stemming. Sentiment labeling was performed using a lexicon-based approach, followed by TF-IDF weighting and Naïve Bayes classification. The developed application provides functionalities for sentiment prediction, performance evaluation, and visualization of sentiment analysis results. Model evaluation in the Streamlit environment achieved an accuracy of 77%, a precision of 80%, a recall of 77%, and an F1-score of 76%. Sentiment distribution analysis revealed that positive sentiment dominated with 64.6% of the comments, followed by negative sentiment at 22.0% and neutral sentiment at 13.4%. These findings indicate that the proposed system is capable of effectively classifying public sentiment and providing valuable insights into visitor perceptions of Lau Berte Waterfall, which may support tourism evaluation and development efforts.