Perbandingan Kinerja Algoritma Naive Bayes dan Logistic Regression Berbasis TF-IDF dalam Klasifikasi Sentimen Komentar YouTube terhadap Layanan Digital Kampus
Performance Comparison of Naive Bayes and Logistic Regression Based on TF-IDF for Sentiment Classification of YouTube Comments on Campus Digital Services
DOI:
https://doi.org/10.57152/malcom.v6i4.2793Keywords:
Analisis Sentimen, Komentar YouTube, Layanan Digital Kampus, Logistic Regression, Naive Bayes, TF-IDFAbstract
Layanan digital kampus, seperti sistem informasi akademik, penerimaan mahasiswa baru online, e-learning, learning management system, dan administrasi akademik online, memunculkan beragam tanggapan dari pengguna di media sosial. Komentar YouTube menjadi sumber umpan balik yang penting, tetapi data yang besar, informal, dan tidak terstruktur membuat analisis manual kurang efisien. Penelitian ini bertujuan untuk mengevaluasi kinerja algoritma Naive Bayes dan Logistic Regression berbasis Term Frequency–Inverse Document Frequency (TF-IDF) dalam mengklasifikasikan sentimen pada komentar YouTube terkait layanan digital kampus. Data penelitian terdiri atas 7.322 komentar yang dikumpulkan menggunakan kata kunci terkait sistem akademik online, LMS kampus, perkuliahan online, pendaftaran mahasiswa baru online, dan layanan digital kampus. Tahapan penelitian meliputi crawling data, preprocessing, pelabelan sentimen, ekstraksi fitur TF-IDF, pelatihan model dengan dan tanpa Synthetic Minority Oversampling Technique (SMOTE), serta evaluasi menggunakan accuracy, precision, recall, F1-score, dan confusion matrix. Hasil menunjukkan 3.181 komentar positif (43,4%), 2.350 negatif (32,1%), dan 1.791 netral (24,5%). Logistic Regression tanpa SMOTE menghasilkan kinerja terbaik dengan accuracy 81,57%, precision 80,77%, recall 80,59%, dan F1-score 80,67%. Temuan ini menunjukkan bahwa Logistic Regression lebih stabil dibandingkan dengan Naive Bayes dalam klasifikasi sentimen komentar YouTube berbahasa Indonesia mengenai layanan digital kampus.
Downloads
References
A. Asro and N. Rukhviyanti, “Big Data-Based YouTube Feedback Analytics Architecture with Generative AI Integration,” vol. 6, no. 2, pp. 788–799, 2026, doi: 10.57152/malcom.v6i2.2626.
D. Y. Saraswati, M. R. Handayani, K. Umam, and M. I. Mustofa, “Sentiment Classification of MyPertamina Reviews Using Naïve Bayes and Logistic Regression,” Journal of Applied Informatics and Computing, vol. 9, no. 4, pp. 1319–1325, Aug. 2025, doi: 10.30871/jaic.v9i4.9723.
H. Barus, I. N. Fajri, and Y. Pristyanto, “Sentiment Classification Analysis of Tokopedia Reviews Using TF-IDF, SMOTE, and Traditional Machine Learning Models,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
A. P. Widyasari, “Sentiment Analysis of YouTube Comments on the 2025 DPR RI Demonstration Using Machine Learning,” 2026. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
I. G. B. A. Budaya and I. K. P. Suniantara, “Comparison of Sentiment Analysis Algorithms with SMOTE Oversampling and TF-IDF Implementation on Google Reviews for Public Health Centers,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 3, pp. 1077–1086, Jul. 2024, doi: 10.57152/malcom.v4i3.1459.
L. Zhang, “Features extraction based on Naive Bayes algorithm and TF-IDF for news classification,” PLoS One, vol. 20, no. 7 July, Jul. 2025, doi: 10.1371/journal.pone.0327347.
Henderi, Asro, A. Sulaiman, T. B. Kurniawan, D. A. Dewi, and M. Alqudah, “Utilizing Sentiment Analysis for Reflect and Improve Education in Indonesia,” Journal of Applied Data Sciences, vol. 6, no. 1, pp. 189–200, Jan. 2025, doi: 10.47738/jads.v6i1.527.
U. N. Jakarta, V. B. Lestari, and C. A. Hutagalung, “Evaluation of TF-IDF Extraction Techniques in Sentiment Analysis of Indonesian-Language Marketplaces Using SVM, Logistic Regression, and Naive Bayes,” pp. 22–2025, Jun. 2025, doi: 10.21009/j.
S. Khoerunnisa, D. F. Shiddieq, and D. Nurhayati, “Penerapan Algoritma Naive Bayes dengan Teknik TF-IDF dan Cross Validation untuk Analisis Sentimen Terhadap Starlink,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 5, no. 2, pp. 566–577, Mar. 2025, doi: 10.57152/malcom.v5i2.1852.
K. Nandini and M. Rahardi, “Sentiment Analysis of Economic Policy Comments on YouTube Using Ensemble Machine Learning,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
A. Angdresey, L. Sitanayah, and I. L. H. Tangka, “Sentiment Analysis for Political Debates on YouTube Comments using BERT Labeling, Random Oversampling, and Multinomial Naïve Bayes,” Journal of Computing Theories and Applications, vol. 2, no. 3, pp. 342–354, Jan. 2025, doi: 10.62411/jcta.11668.
M. Tsiourlini, K. Tzafilkou, D. Karapiperis, and C. Tjortjis, “Text Analytics on YouTube Comments for Food Products,” Information (Switzerland), vol. 15, no. 10, Oct. 2024, doi: 10.3390/info15100599.
G. S. Rasyad and W. Maharani, “Logistic Regression and Naïve Bayes Comparison in Classifying Emotions on Indonesian X Social Media,” Edumatic: Jurnal Pendidikan Informatika, vol. 9, no. 1, pp. 31–40, Apr. 2025, doi: 10.29408/edumatic.v9i1.29120.
J. Chaidir and J. Friadi, “Zona Teknik: Jurnal Ilmiah Evaluasi Kinerja Algoritma Klasifikasi dalam Studi Kasus Prediksi Kelulusan di Universitas XYZ,” vol. 19, no. 1, pp. 15–22, 2025, doi: 10.37776/zt.vxix.xxx.
K. Shanmugavadivel, M. Subramanian, P. V, and P. chinnappan D, “InnovationEngineers@DravidianLangTech-EACL 2024: Sentimental Analysis of YouTube Comments in Tamil by using Machine Learning,” in Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, Stroudsburg, PA, USA: Association for Computational Linguistics, 2024, pp. 262–265. doi: 10.18653/v1/2024.dravidianlangtech-1.44.
H. L. A. Asro, A. Wicaksono, and P. Herwanto, “Strategi Dinamis Menggunakan MongoDB untuk Analisis Sentimen terhadap Komentar YouTube Pilkada Gubernur Indonesia 2024,” 2024. [Online]. Available: https://jurnaldrpm.budiluhur.ac.id/index.php/Kresna/
Susan Juli Safitri, Gelar Alam Ramdhaniawan, Asro Asro, and Novi Rukhviyanti, “Analisis Literatur Review Perencanaan Strategi Sistem Informasi Menggunakan Metode Metode Five Competitive Force Pada CV. Bio Chitosan Indonesia,” Bridge?: Jurnal publikasi Sistem Informasi dan Telekomunikasi, vol. 2, no. 4, pp. 319–327, Sep. 2024, doi: 10.62951/bridge.v2i4.263.
I. G. B. A. Budaya and I. K. P. Suniantara, “Comparison of Sentiment Analysis Algorithms with SMOTE Oversampling and TF-IDF Implementation on Google Reviews for Public Health Centers,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 3, pp. 1077–1086, Jul. 2024, doi: 10.57152/malcom.v4i3.1459.
S. Khoerunnisa, D. F. Shiddieq, and D. Nurhayati, “Penerapan Algoritma Naive Bayes dengan Teknik TF-IDF dan Cross Validation untuk Analisis Sentimen Terhadap Starlink,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 5, no. 2, pp. 566–577, Mar. 2025, doi: 10.57152/malcom.v5i2.1852.
Chely Aulia Misrun, E. Haerani, M. Fikry, and E. Budianita, “Analisis sentimen komentar youtube terhadap Anies Baswedan sebagai bakal calon presiden 2024 menggunakan metode naive bayes classifier,” Jurnal CoSciTech (Computer Science and Information Technology), vol. 4, no. 1, pp. 207–215, Apr. 2023, doi: 10.37859/coscitech.v4i1.4790.
R. F. Awaliyah and A. Hendrawan, “Comparative Sentiment Analysis on Mobile JKN Application Using Logistic Regression with SMOTE Based Statistical Feature Selection,” Journal of Applied Informatics and Computing, vol. 9, no. 6, pp. 3945–3952, Dec. 2025, doi: 10.30871/jaic.v9i6.10520.
H. Sapta Mawar and M. Rahardi, “Sentiment Analysis of the TPKS Law on Twitter: A Comparative Study of Classification Algorithm Performance,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
A. Mccallum and K. Nigam, “A Comparison of Event Models for Naive Bayes Text Classification,” 1998. [Online]. Available: www.aaai.org
D. W. . Hosmer, Stanley. Lemeshow, and R. X. . Sturdivant, Applied logistic regression. Wiley, 2013.
N. Sulistianingsih and I. N. Switrayana, “Enhancing Sentiment Analysis for the 2024 Indonesia Election Using SMOTE-Tomek Links and Binary Logistic Regression,” International Journal of Education and Management Engineering, vol. 14, no. 3, pp. 22–32, Jun. 2024, doi: 10.5815/ijeme.2024.03.03.
O. El?Azzouzy, T. Chanyour, and S. J. Andaloussi, “Transformer-based models for sentiment analysis of YouTube video comments,” Sci. Afr., vol. 29, Sep. 2025, doi: 10.1016/j.sciaf.2025.e02836.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Aulia Indah Dwi Lestari, Hendra Gunawan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright © by Author; Published by Institut Riset dan Publikasi Indonesia (IRPI)
This Indonesian Journal of Machine Learning and Computer Science is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
