<![CDATA[One of the features introduced by the TikTok platform is TikTok Shop, where sellers and buyers can interact easily through the live broadcast feature and promote products within the TikTok application without having to switch to other applications, as well as offering products at very cheap prices. However, this causes dissatisfaction from small traders who find it difficult to compete. Opinions about the TikTok Shop feature have created various responses from the public. This research aims to analyze public sentiment towards the TikTok Shop feature using Twitter as a data source. Applying the Naive Bayes Classifier (NBC) and K-Nearest Neighbor (KNN) algorithms and dividing data using 10-Fold Cross Validation. Labeling was carried out using the clustering method using the K-Means algorithm, divided into three categories positive, negative and neutral. The addition of qualitative data analysis techniques with thematic analysis method in this research aims to find patterns or themes in the data. The labeling results show that 75% of the total data expresses negative sentiment towards the TikTok Shop feature. And the results of the thematic analysis found that the main theme, namely "Inappropriate regulations", covers 32% of the data, with a total of 754. This research concludes that the KNN method is superior to NBC, with better accuracy, precision and recall. This is in line with previous research that KNN is superior to nave Bayes, but other research shows the opposite where nave Bayes is superior to KNN. Further research can be carried out to improve the performance of these two algorithms in sentiment analysis, for example by using more sophisticated preprocessing methods, more representative feature extraction, or more efficient optimization techniques.]]>
