@phdthesis{digilib78701,
           month = {August},
           title = {PERBANDINGAN METODE K-NEAREST NEIGHBOR (KNN) DAN RANDOM FOREST UNTUK KLASIFIKASI SENTIMEN KOMENTAR DI TIKTOK  (STUDI KASUS: PERFORMA ONIC ESPORTS PADA TURNAMEN M7 MOBILE LEGENDS: BANG BANG)},
          school = {UIN SUNAN KALIJAGA YOGYAKARTA},
          author = {NIM.: 22106010075 Anggit Pratiknyo Widyagiri},
            year = {2026},
            note = {Muchammad Abrori, S.Si., M.Kom dan Muhammad Rashif Hilmi, S.Si., M.Sc.},
        keywords = {Analisis Sentimen, Tiktok, K-Nearest Neighbor, Random Forest, TF-IDF, Mobile Legends: Bang Bang},
             url = {https://digilib.uin-suka.ac.id/id/eprint/78701/},
        abstract = {The performance of ONIC Esports in the M7 Mobile Legends: Bang Bang (MLBB) tournament generated various opinions among TikTok users, making sentiment analysis necessary to classify comments into positive, negative, and neutal categories. This study aims to identify the stages of sentiment classification using the k-Nearest Neighbor (kNN) and Random Forest methods, analyze the sentiment classification result, and compare the performance of both methods. The study used 5,203 Indonesian language comments collected through web scraping. The data were processed through labelling, preprocessing, and Term Frequency-Inverse Document Frequency (TF-IDF) feature extraction before being classified using kNN and Random Forest with Grid Search and 5-Fold Cross Validation. Model performance was evaluated using a confusion matrix, accuracy, precision, recall, and F1-score. The result showed that Random Forest achieved the best performance with an accuracy of 83,18\%, while kNN using Euclidean and Manhattan distances achieved accuracies of 79.49\% and 64.82\%, respectively. Therefore, Random Forest outperformed kNN in classifying TikTok comments related to the performance of ONIC Esports in the M7 MLBB tournament.}
}