Perbandingan Kinerja SVM, Random Forest dan XGBoost pada Aplikasi Access by KAI Menggunakkan ADASYN
DOI:
https://doi.org/10.30865/jurikom.v12i5.9139Keywords:
Machine Learning, Support Vector Machine (SVM), Random Forest., Long Short Term Memory, Adaptive Synthetic Sampling (ADASYN)Abstract
The rapid growth of digital applications has heightened the need to understand user perceptions more thoroughly, particularly through sentiment analysis of user-generated reviews. In practice, sentiment classification often faces challenges related to class imbalance, especially when neutral reviews are significantly fewer than positive or negative ones. This imbalance can limit a model’s ability to accurately detect all sentiment categories. This study examines the comparative performance of three machine learning algorithms Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) by applying the Adaptive Synthetic Sampling (ADASYN) technique to address class imbalance. This study differs from previous similar research by conducting a simultaneous comparative analysis of three algorithms using the ADASYN method in the context of Access by KAI application reviews, which has not been examined in prior studies. Experimental results indicate that after implementing ADASYN, model accuracies reached 75.17% for SVM, 84.06% for RF, and 83.17% for XGBoost. Although accuracy slightly decreased after oversampling, the F1-scores for the neutral class improved to 0.13 (SVM), 0.05 (RF), and 0.14 (XGBoost). Before applying ADASYN, the models achieved accuracies of 85.88% (SVM), 85.13% (RF), and 85.37% (XGBoost), but they were unable to effectively recognize neutral sentiments, with F1-scores of 0.00 for SVM and RF, and 0.03 for XGBoost. These findings suggest that ADASYN enhances model sensitivity to neutral sentiment, with XGBoost demonstrating the most consistent and robust performance in sentiment classification for the Access by KAI application.
References
[1] R. Damanhuri and V. A. Husein, “Analisis Sentimen pada Ulasan Aplikasi Access by KAI Berbahasa Indonesia Menggunakan Word-Embedding dan Classical Machine Learning,” J. Masy. Inform., vol. 15, no. 2, pp. 97–106, 2024, doi: 10.14710/jmasif.15.2.62383.
[2] D. Purnamasari et al., Pengantar Metode Analisis Sentimen. 2023.
[3] N. A. Jiana and B. Hartono, “Sentimen Analisa Ulasan Aplikasi Access by KAI pada Google Play Store menggunakan Algoritma K-NN,” J. Media Inform. Budidarma, vol. 8, no. 3, p. 1388, 2024, doi: 10.30865/mib.v8i3.7730.
[4] M. A. S. Nugroho, D. Susilo, and D. Retnoningsih, “Analisis Sentimen Ulasan Aplikasi ”Access by KAI” Menggunakan Algoritma Machine Learning,” J. Tek. Inf. dan Komput., vol. 7, no. 2, p. 820, 2024, doi: 10.37600/tekinkom.v7i2.1854.
[5] D. L. Devi, A. A. Arifiyanti, and S. F. A. Wati, “Analisis Sentimen Ulasan Pengguna Access by KAI Menggunakan Metode Word2Vec Dan Algoritma Svm,” J. Inform. dan Tek. Elektro Terap., vol. 12, no. 3, 2024, doi: 10.23960/jitet.v12i3.4892.
[6] E. Rizqi Mar’atus Sholiihah, I. G. Susrama Mas Diyasa, and E. Yulia Puspaningrum, “Perbandingan Kinerja Kernel Linear Dan Rbf Support Vector Machine Untuk Analisis Sentimen Ulasan Pengguna Kai Access Pada Google Play Store,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 1, pp. 728–733, 2024, doi: 10.36040/jati.v8i1.8800.
[7] R. D. Wahyuni and A. N. Utomo, “Penggunaan Metode Lexicon Untuk Analisis Sentimen pada Ulasan Aplikasi KAI Access di Google Play Store,” J. Rekayasa Inf., vol. 11, no. 2, pp. 134–145, 2022.
[8] O. Oktafia and R. S. A. Nugroho, “Comparison of Support Vector Machine(Svm), Xgboost and Random Forest for Sentiment Analysis of Bumble App User Comments,” Proxies J. Inform., vol. 6, no. 1, pp. 32–46, 2024, doi: 10.24167/proxies.v6i1.12453.
[9] I Gusti Ngurah Ady Kusuma, I Made Pradipta, I Made Ari Santosa, and I Komang Dharmendra, “Penanganan Ketidakseimbangan Data Pada Klasifikasi Pengaduan Masyarakat,” J. Teknol. Inf. dan Komput., vol. 9, no. 5, pp. 489–496, 2023, doi: 10.36002/jutik.v9i5.2643.
[10] D. V. Ramadhanti, R. Santoso, and T. Widiharih, “Perbandingan Smote Dan Adasyn Pada Data Imbalance Untuk Klasifikasi Rumah Tangga Miskin Di Kabupaten Temanggung Dengan Algoritma K-Nearest Neighbor,” J. Gaussian, vol. 11, no. 4, pp. 499–505, 2023, doi: 10.14710/j.gauss.11.4.499-505.
[11] F. Fauzi, I. Ismatullah, and I. M. Nur, “Adaptive Synthetic Support Vector Machine Multiclass untuk mengklasifikasikan Imbalance data pada Sentimen kenaikan Bahan Bakar Minyak,” Pros. Semin. Nas. Sains Data, vol. 3, no. 1, pp. 304–312, 2023, doi: 10.33005/senada.v3i1.127.
[12] M. Imani, A. Beikmohammadi, and H. R. Arabnia, “Comprehensive Analysis of Random Forest and XGBoost Performance with SMOTE, ADASYN, and GNUS Under Varying Imbalance Levels,” Technologies, vol. 13, no. 3, pp. 1–40, 2025, doi: 10.3390/technologies13030088.
[13] S. A. S. Mola, Y. C. Luttu, and D. N. Rumlaklak, “Perbandingan Metode Machine Learning dalam Analisis Sentimen Komentar Pengguna Aplikasi InDriver pada Dataset Tidak Seimbang,” J. Sist. Inf. Bisnis, vol. 14, no. 3, pp. 247–255, 2024, doi: 10.21456/vol14iss3pp247-255.
[14] H. N. Zuhdi and B. Prasetiyo, “Analisis Sentimen pada Ulasan Aplikasi iPusnas di Google Play StoreMenggunakan Naive Bayes Classifier,” J. Homepage https//journal.irpi.or.id/index.php/ijirse, vol. 5, no. 1, pp. 12–19, 2025.
[15] S. Nachwa et al., “Pendekatan Klasifikasi Dalam Knowledge Discovery Untuk Analisis Sentimen Berbasis Aspek Pada Ulasan Bandara Sultan Mahmud Badaruddin Ii Di Google Maps,” JATI (Jurnal Mhs. Tek. Inform., vol. 9, no. 3, pp. 4782–4789, 2025, doi: 10.36040/jati.v9i3.13776.
[16] 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 Indones. J. Mach. Learn. Comput. Sci., vol. 4, no. 3, pp. 1077–1086, 2024, doi: 10.57152/malcom.v4i3.1459.
[17] E. D. Madyatmadja, Shinta, D. Susanti, F. Anggreani, and D. J. M. Sembiring, “Sentiment Analysis on User Reviews of Mutual Fund Applications,” J. Comput. Sci., vol. 18, no. 10, pp. 885–895, 2022, doi: 10.3844/jcssp.2022.885.895.
[18] M. Kumar, L. Khan, and H. T. Chang, “Evolving techniques in sentiment analysis: a comprehensive review,” PeerJ Comput. Sci., vol. 11, pp. 1–61, 2025, doi: 10.7717/PEERJ-CS.2592.
[19] D. A. Agustina, S. Subanti, and E. Zukhronah, “Implementasi Text Mining Pada Analisis Sentimen Pengguna Twitter Terhadap Marketplace di Indonesia Menggunakan Algoritma Support Vector Machine,” Indones. J. Appl. Stat., vol. 3, no. 2, p. 109, 2021, doi: 10.13057/ijas.v3i2.44337.
[20] A. Nugroho and A. Husin, “Performance Analysis of Random Forest Using Attribute Normalization,” Sistemasi, vol. 11, no. 1, p. 186, 2022, doi: 10.32520/stmsi.v11i1.1681.
[21] I. G. A. N. Lestari, N. M. R. M. Dewi, K. G. Meiliana, and I. K. A. A. Aryanto, “Effectiveness of AdaBoost and XGBoost Algorithms in Sentiment Analysis of Movie Reviews,” J. Appl. Informatics Comput., vol. 9, no. 2, pp. 258–264, 2025, doi: 10.30871/jaic.v9i2.9077.
[22] M. I. Anugrah, J. Zeniarja, and D. S. Setiawan, “Peningkatan Performa Model Hard Voting Classifier dengan Teknik Oversampling ADASYN pada Penyakit Diabetes,” Edumatic J. Pendidik. Inform., vol. 8, no. 1, pp. 290–299, 2024, doi: 10.29408/edumatic.v8i1.25838.
[23] C. Magnolia, A. Nurhopipah, and B. A. Kusuma, “Penanganan Imbalanced Dataset untuk Klasifikasi Komentar Program Kampus Merdeka Pada Aplikasi Twitter,” Edu Komputika J., vol. 9, no. 2, pp. 105–113, 2022, doi: 10.15294/edukomputika.v9i2.61854.
[24] N. F. Putri, M. F. Hidayattullah, and D. I. Af’idah, “Sentimen Analisis Kota Tegal Berbasis Aspek Menggunakan Algoritma Naïve Bayes,” Infomatek, vol. 26, no. 1, pp. 45–54, 2024, doi: 10.23969/infomatek.v26i1.11209.
