PERFORMANCE ANALYSIS OF MACHINE LEARNING AND INDOBERT IN CLASSIFYING SENTIMENTS ON INDONESIA'S FREE NUTRITIOUS MEAL
DOI:
https://doi.org/10.22373/cj.v10i1.33886Keywords:
social media, platform X, NLP, deep learning, classificationAbstract
Natural Language Processing (NLP) is a branch of artificial intelligence that is widely used to analyze whether a sentence contains positive, negative, or neutral sentiment, particularly in the context of expressing opinions in the online environment. This study compares several models to identify the most optimal one, namely Naïve Bayes, Support Vector Machine (SVM), XGBoost, and IndoBERT. The dataset used in this research was obtained from Kaggle and consists of 5,644 data points in the neutral class, 2,934 data points in the positive class, and 2,606 data points in the negative class. Prior to model implementation, the dataset underwent a preprocessing stage that included case folding, cleansing, tokenization, stemming, and stopword removal. Subsequently, the data were trained using the four aforementioned methods. The results indicate that Naïve Bayes achieved an accuracy of 75%, SVM reached 79%, XGBoost obtained 76%, while IndoBERT achieved the highest accuracy at 85%. Therefore, it can be concluded that, using this dataset, IndoBERT performed sentiment classification very effectively.
Downloads
References
Indonesian Internet Service Providers Association (APJII), “Lanskap Pengguna Internet Indonesia 2025_ Koneksi Meluas, Literasi Masih Lemas – internetsehat.” 2025, [Online]. Available: https://internetsehat.id/.
F. Sudirjo, K. Diantoro, J. A. Al-gasawneh, H. K. Azzaakiyyah, and M. A. Ausat, “Application of ChatGPT in Improving Customer Sentiment Analysis for Businesses,” vol. 5, no. 3, pp. 283–288, 2023, [Online]. Available: https://doi.org/10.47233/jteksis.v5i3.871 .
H. Taherdoost and M. Mitra, “Artificial Intelligence and Sentiment Analysis: A Review in Competitive Research.” pp. 1–15, 2023.
S. W. Nisa Akbarilah Putri, Anindya Apriliyanti Pravitasari, “Topic-based sentiment analysis of Jamsostek mobile application reviews using the BERTopic method,” Commun. Math. Biol. Neurosci, pp. 1–20, 2026, [Online]. Available: https://doi.org/10.28919/cmbn/9682.
R. Hajrizi and K. P. Nuçi, “Aspect-Based Sentiment Analysis in Education Domain,” 2020.
T. Shaik, X. Tao, C. Dann, H. Xie, Y. Li, and L. Galligan, “Sentiment analysis and opinion mining on educational data: A survey,” Nat. Lang. Process. J., vol. 2, no. December 2022, p. 100003, 2023, doi: 10.1016/j.nlp.2022.100003.
S. Adi, S. Mola, Y. T. Polly, and Y. C. Atok, “Analisis Sentimen Terhadap Data Komentar Publik Mengenai Isu UU Pilkada 2024 Menggunakan Metode Naïve Bayes dan K-Nearest Neighbor,” vol. 5, no. 3, pp. 337–343, 2025, doi: 10.47065/jimat.v5i3.514.
A. Haris, K. Sandi, E. Haerani, L. Oktavia, and F. Kurnia, “Klasifikasi Sentimen Masyarakat Terhadap Revisi Undang-Undang Tentara Nasional Indonesia Menggunakan Naïve Bayes Classifier,” vol. 5, no. 4, pp. 594–603, 2025, doi: 10.47065/bulletincsr.v5i4.615.
A. A. Nurhasananda and M. Akbar, “Analisis Sentimen Masyarakat Terhadap Kebijakan Undang-Undang Tentara Nasional Indonesia (UU TNI) Menggunakan Support Vector Machine,” vol. 5, no. 1, pp. 1–14, 2025, [Online]. Available: https://doi.org/10.53697/jkomitek.v5i1.2603.
J. Li, Z. Li, X. Ma, Q. Zhao, C. Zhang, and G. Yu, “Sentiment Analysis on Online Videos by Time-Sync Comments,” entropy, vol. 25, no. 1016, pp. 1–18, 2023, [Online]. Available: https://doi.org/10.3390/%0Ae25071016.
D. A. Musleh, I. Alkhwaja, A. Alkhwaja, and M. Alghamdi, “Arabic Sentiment Analysis of YouTube Comments: NLP-Based Machine Learning Approaches for Content Evaluation,” Big Data Cogn. Comput., vol. 7, no. 127, pp. 1–16, 2023, [Online]. Available: https://doi.org/10.3390/bdcc7030127%0A.
R. Singh and A. Tiwari, “Youtube Comments Sentiment Analysis,” Int. J. Sci. Res. Eng. Manag., vol. 05, no. 05, pp. 1–11, 2021.
R. Danar, D. M. Kom, and M. M. Kom, “Dasar Dasar Natural Language Processing ( NLP ).”
W. Nurharjadmo, F. Ansoriyah, and M. A. Khadija, “Analyzing Public Perception using Aspect Based Sentiment Analysis : Case Study of Capital Relocation Planning of Indonesia,” 2024 7th Int. Conf. Informatics Comput. Sci., pp. 191–196, 2024, doi: 10.1109/ICICoS62600.2024.10636903.
Kaggle“MBG 06 Januari - 06 Oktober 2025.” Kaggle, [Online]. Available: https://www.kaggle.com/datasets/ravhihz/mbg-06-januari-06-oktober-2025.
A. P. Maretta and A. Meiriza, “Aspect-Based Sentiment Analysis of Hospital Service Reviews Using Fine- Tuned IndoBERT,” vol. 9, no. 5, 2025.
E. Puspita, D. F. Shiddieq, and F. F. Roji, “Topic Modeling on Online News Media Using Latent Diriclet Allocation ( Case Study Somethinc Brand ) Pemodelan Topik pada Media Berita Online Menggunakan Latent Dirichlet Allocation ( Studi Kasus Merek Somethinc ),” vol. 4, no. April, pp. 481–489, 2024.
V. Cerqueira, L. Torgo, P. Branco, and C. Bellinger, “Automated imbalanced classification via layered learning,” Machine Learning, vol. 112, no. 6, pp. 2083–2104, 2023, doi: 10.1007/s10994-022-06282-w.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Maulyanda, Sri Azizah Nazhifah, Syafrial Fachri Pane, Irvanizam Irvanizam
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with Cyberspace Journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
