Sentiment Analysis on Tiktok App Reviews on Google Play Store Using The Naive Bayes Approach

Abstract

The TikTok application has gained global popularity, leading to a surge of user reviews on platforms such as the Google Play Store. This study aims to analyze user sentiment using the Naive Bayes algorithm by classifying reviews into positive and negative categories. The dataset, consisting of 1,914 user reviews, underwent preprocessing through case folding, stopword removal, and lemmatization. Sentiment labeling was carried out using TextBlob, and classification performance was evaluated using K-Fold Cross Validation and a confusion matrix. Results indicate that the Naive Bayes model achieved an average accuracy of 82.76%, demonstrating its effectiveness in identifying sentiment in user-generated content. Despite certain limitations, such as the absence of neutral sentiment and class imbalance, this research provides valuable insights into user perceptions of the TikTok app and highlights the importance of textual context in sentiment classification. For future work, it is recommended to expand the sentiment categories by including neutral labels and to experiment with other classification algorithms or deep learning approaches to improve accuracy and generalizability