An Ensemble Learning Approach for Sentiment Analysis of Maxim Application Reviews Using SVM, KNN, and Random Forest
DOI:
https://doi.org/10.30871/jaic.v9i6.11447Keywords:
Ensemble Learning, K-Nearest Neighbor, Random Forest, Sentiment Analysis, Support Vector MachineAbstract
The development of online transportation applications such as Maxim has increased the need for sentiment analysis to understand user opinions from reviews on the Google Play Store. The main challenges in this analysis are language diversity, variations in writing style, and data imbalance, which affect model accuracy. This study aims to evaluate the performance of the Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest (RF) algorithms, as well as ensemble approaches through the Voting Classifier and Combined Classifier, in sentiment analysis of Maxim app reviews. The dataset consists of 2,851 Indonesian-language reviews collected through web scraping from the Google Play Store in 2025. Sentiment labels were automatically determined based on user ratings, where ratings of 4–5 were categorized as positive and ratings below 4 as negative, with an initial distribution of 2,295 positive and 556 negative reviews before balancing using SMOTE–Tomek Links. Preprocessing steps included case folding, tokenization, stopword removal, and stemming using Sastrawi, while feature weighting was performed with unigram TF-IDF. The Combined Classifier merged the probability scores from the SVM, KNN, and RF models to produce the final prediction. Evaluation was conducted using 5-Fold Cross Validation with accuracy, precision, recall, F1-score, and ROC-AUC as evaluation metrics. The results show that RF and the Combined Classifier achieved the best performance with 85% accuracy, 87% precision, 85% recall, 86% F1-score, and 0.91 ROC-AUC, while SVM and the Voting Classifier ranked in the middle and KNN ranked the lowest. These findings confirm that ensemble learning, particularly the Combined Classifier, effectively improves the accuracy and stability of review classification compared to individual methods.
Downloads
References
[1] U. Herni, “Analisis Sentimen dari Aplikasi Shopee Indonesia Menggunakan,” Indones. J. Appl. Stat., vol. 5, no. 1, pp. 31–38, 2022.
[2] M. J. Sai, P. Chettri, R. Panigrahi, A. Garg, A. K. Bhoi, and P. Barsocchi, “An Ensemble of Light Gradient Boosting Machine and Adaptive Boosting for Prediction of Type-2 Diabetes,” Int. J. Comput. Intell. Syst., vol. 16, no. 1, 2023.
[3] Y. B. Lasotte, E. J. Garba, Y. M. Malgwi, and M. A. Buhari, “An Ensemble Machine Learning Approach for Fake News Detection and Classification Using a Soft Voting Classifier,” Eur. J. Electr. Eng. Comput. Sci., vol. 6, no. 2, pp. 1–7, 2022.
[4] K. Suresh Kumar et al., “Sentiment Analysis of Short Texts Using SVMs and VSMs-Based Multiclass Semantic Classification,” Appl. Artif. Intell., vol. 38, no. 1, 2024.
[5] Idris I, Mustofa Y, and Salihi I, “Analisis Sentimen Terhadap Penggunaan Aplikasi Shopee Mengunakan Algoritma Support Vector Machine (SVM),” Jambura J. Electr. Electron. Eng., vol. 5, pp. 32–35, 2023.
[6] F. Kurniawan and T. Supriyatno, “A contest of sentiment analysis: k-nearest neighbor versus neural network,” IAES Int. J. Artif. Intell., vol. 14, no. 2, pp. 1625–1633, 2025.
[7] K. Nugroho, E. Winarno, D. R. I. M. Setiadi, and O. Farooq, “Enhanced multi-lingual Twitter sentiment analysis using hyperparameter tuning k-nearest neighbors,” Bull. Electr. Eng. Informatics, vol. 13, no. 6, pp. 4327–4334, 2024.
[8] J. J. Sanchez-Medina, “Sentiment analysis and random forest to classify LLM versus human source applied to Scientific Texts,” pp. 1–12, 2024.
[9] J. Song et al., “The random forest model has the best accuracy among the four pressure ulcer prediction models using machine learning algorithms,” Risk Manag. Healthc. Policy, vol. 14, pp. 1175–1187, 2021.
[10] Muhammad Nur Akbar, Nur Hasanahlmar’iyah Rusydi, M. Hasrul H., Nurul Shaumi Ramadhanti, and Erfiana, “Sentiment Analysis of Review Aplikasi Maxim di Google Play Store Menggunakan Support Vector Machine (SVM),” AGENTS (Jurnal Sist. Informasi), vol. 2, no. 2, pp. 1–8, 2022.
[11] S. Syahrudin, Fenilinas Adi Artanto, Ahmad Rifqi Maulana, and F. Filsafat, “Metode Support Vector Machine (SVM) dan Lexicon-Based dalam Analisis Sentiment Ulasan Pengguna Aplikasi Wink,” JUMINTAL J. Manaj. Inform. dan Bisnis Digit., vol. 4, no. 1, pp. 59–73, 2025.
[12] F. T. Kurniati, D. H. Manongga, E. Sediyono, S. Y. J. Prasetyo, and R. R. Huizen, “Object Classification Model Using Ensemble Learning with Gray-Level Co-Occurrence Matrix and Histogram Extraction,” J. Ilm. Tek. Elektro Komput. dan Inform., vol. 9, no. 3, pp. 793–801, 2023.
[13] M. Periasamy, R. Mahadevan, B. L. S, R. C. Raman, H. K. S, and J. Jessiman, “Finding fake reviews in e-commerce platforms by using hybrid algorithms,” 2024.
[14] N. V. R. Jhosefhin and C. Dewi, “Analisis Sentimen Crawling Data dari Sosial Media X tentang Gaza Menggunakan Metode SVM dan Decision Tree,” J. Indones. Manaj. Inform. dan Komun., vol. 6, no. 1, pp. 427–437, 2025.
[15] T. A. Zuraiyah, M. M. Mulyati, and G. H. F. Harahap, “Perbandingan Metode Naïve Bayes, Support Vector Machine Dan Recurrent Neural Network Pada Analisis Sentimen Ulasan Produk E-Commerce,” Multitek Indones., vol. 17, no. 1, pp. 27–43, 2023.
[16] F. Suandi et al., Enhancing Sentiment Analysis Performance Using SMOTE and Majority Voting in Machine Learning Algorithms, no. Icae 2024. Atlantis Press International BV, 2024.
[17] Y. A. Mustofa, I. Surya, and K. Idris, “Pendekatan Ensemble pada Analisis Sentimen Ulasan Aplikasi Google Play Store Ensemble Approach to Sentiment Analysis of Google Play Store App Reviews,” Jambura J. Electr. Electron. Eng., vol. 6, no. 2, pp. 181–188, 2024.
[18] T. N. Wijaya, R. Indriati, and M. N. Muzaki, “Analisis Sentimen Opini Publik Tentang Undang-Undang Cipta Kerja Pada Twitter,” Jambura J. Electr. Electron. Eng., vol. 3, no. 2, pp. 78–83, 2021.
[19] R. Sakti et al., “Review of Literature on Improving the KNN Algorithm,” Trans. Mach. Learn. Artif. Intell., vol. 11, no. 3, pp. 63–72, 2023.
[20] A. Alsayat, “Improving Sentiment Analysis for Social Media Applications Using an Ensemble Deep Learning Language Model,” Arab. J. Sci. Eng., vol. 47, no. 2, pp. 2499–2511, 2022.
[21] D. Ghoul, J. Patrix, G. Lejeune, and J. Verny, “A combined AraBERT and Voting Ensemble classifier model for Arabic sentiment analysis,” Nat. Lang. Process. J., vol. 8, no. December 2023, p. 100100, 2024.
[22] L. Rohmatun and A. Baita, “Machine Learning-Based Sentiment Analysis on Twitter ( X ): A Case Study of the ‘ Kabur Aja Dulu ’ Issue Using SVM,” vol. 9, no. 4, pp. 1972–1983, 2025.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Ruth Mei Sasmita, Allsela Meiriza, Hardini Novianti
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this 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 (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) 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).
