Penerapan Support Vector Machine Dengan Smote Untuk Klasifikasi Sentimen Pada Data Ulasan Aplikasi Trading View
DOI:
https://doi.org/10.47065/bulletincsr.v6i1.793Keywords:
Sentiment Analysis; Support Vector Machine; Synthetic Minority Over-sampling Technique; Application Reviews; TradingView; Sentiment ClassificationAbstract
In the digital era, user feedback on mobile applications serves as highly valuable information for developers to evaluate app performance. One popular application in the field of finance and investment is TradingView, widely used for technical analysis by traders. User feedback on this application reflects various user sentiments, including positive, negative, and neutral. However, the large volume of reviews and the unstructured nature of text data make manual analysis inefficient and prone to high subjective bias. Therefore, the use of automatic classification methods capable of processing text data with reasonable accuracy is required.
This study aims to implement the “Support Vector Machine (SVM)” technique to classify user feedback on the TradingView application. To address the issue of imbalanced sentiment class distribution, the study also employs the “Synthetic Minority Over-sampling Technique (SMOTE)”. The study utilizes 10,000 reviews obtained via web scraping from the Google Play Store. The study workflow consists of text preprocessing, feature extraction using “Term Frequency-Inverse Document Frequency (TF-IDF)”, data balancing, SVM model training, and model evaluation. The evaluation results show that the application of SVM with SMOTE achieves an accuracy of approximately ±85.56% across data splits (70:30, 80:20, 90:10). In each scenario, the highest F1-score was achieved for the positive sentiment class, while the performance of minority classes (negative and neutral) improved after data balancing with SMOTE, with an average F1-score increase of 1.67% for the negative class and 10.67% for the neutral class. Without SMOTE, the average negative F1-score was ±57%, and the neutral class was undetected (0.00%). Furthermore, validation using K-Fold Cross Validation yielded an average accuracy of 89.20%, which increased to 95.10% after applying SMOTE. This improvement was consistent across all data proportions (70:30, 80:20, 90:10), with an average increase of 5.44%. These findings confirm that integrating SVM with SMOTE not only enhances classification performance on imbalanced data but also maintains model stability. Therefore, this study contributes to the advancement of automated sentiment classification systems, particularly for financial mobile app reviews, and can serve as a reference for future research in user review analysis on similar applications.
Downloads
References
B. A. Maulana, M. J. Fahmi, A. M. Imran, and N. Hidayati, “Analisis Sentimen Terhadap Aplikasi Pluang Menggunakan Algoritma Naive Bayes dan Support Vector Machine (SVM),” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 4, no. 2, pp. 375–384, Feb. 2024, doi: 10.57152/malcom.v4i2.1206.
A. Muhammadin and I. A. Sobari, “Analisis Sentimen Pada Ulasan Aplikasi Kredivo Dengan Algoritma SVM Dan NBC,” Reputasi:Jurnal Rekayasa Perangkat Lunak, vol. 2, no. 2, pp. 85–91, 2021, doi: 10.31294/reputasi.v2i2.785.
H. Eldo, Ayuliana, D. Suryadi, G. Chrisnawati, and L. Judijanto, “Penggunaan Algoritma Support Vector Machine (SVM) Untuk Deteksi Penipuan pada Transaksi Online,” J. Minfo Polgan, vol. 13, no. 2, pp. 1627–1632, Oct. 2024, doi: 10.33395/jmp.v13i2.14186.
A. A. Nurrahman, M. Mauladi, and A. Rahman, “Analisis Sentimen Masyarakat terhadap Kenaikan Harga Bahan Bakar Minyak Menggunakan Support Vector Machine dan SMOTE,” sudo J. Tek. Inform., vol. 4, no. 2, pp. 50–56, 2025, doi: 10.56211/sudo.v4i2.908.
Muhammad Ibnu Choldun Rachmatullah, Sari Armiati, and Mubassiran, “Menerapkan Smote pada Klasifikasi Data Penyakit Stroke,” Improv. Ilm. Manaj. Tek. Inform., vol. 17, no. 1, pp. 9–12, 2025, [Online]. Available: https://ejurnal.ulbi.ac.id/index.php/improve/article/view/4307
M. I. Putri and I. Kharisudin, “Analisis Sentimen Pengguna Aplikasi Marketplace Tokopedia Pada Situs Google Play Menggunakan Metode Support Vector Machine (SVM), Naïve Bayes, dan Logistic Regression,” Prism. Pros. Semin. Nas. Mat., vol. 5, pp. 759–766, 2022, [Online]. Available: https://journal.unnes.ac.id/sju/index.php/prisma/
E. Eskiyaturrofikoh and R. R. Suryono, “Analisi Sentimen Aplikasi X pada Google Play Store Menggunakan Algoritma Naive Bayes dan Suport Vector Machine (SVM),” JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 9, no. 3, pp. 1408–1419, Aug. 2024, doi: 10.29100/jipi.v9i3.5392.
A. Mulianti, Y. Chrisnanto, and H. Ashaury, “Optimalisasi Klasifikasi Support Vector Machine dengan SMOTE: Studi Kasus Ulasan Pengguna Aplikasi Alfagift,” J. Pekommas, vol. 9, no. 2, pp. 249–258, Dec. 2024, doi: 10.56873/jpkm.v9i2.5583.
V. Alessandro Riyanto and D. Budi Santoso, “Penerapan Model Support Vector Machine Pada Klasifikasi Sentimen Ulasan Aplikasi Lazada,” J. Ris. Sist. Inf. Dan Tek. Inform., vol. 9, no. 1, pp. 178–184, 2024, doi: 10.30645/jurasik.v9i1.725.
T. Sugihartono, R. Rian, and C. Putra, “Penerapan Metode Support Vector Machine dalam Classifikasi Ulasan Pengguna Aplikasi Mobile JKN,” SKANIKASistem Komput. dan Tek. Inform., vol. 7, no. 2, pp. 144–153, Jul. 2024, doi: 10.36080/skanika.v7i2.3193.
A. Chapagain, Hands-on Web Scraping with Python: Extract Quality Data from the Web Using Effective Python Techniques. Birmingham, UK: Packt Publishing, 2023.
G. Radiena and A. Nugroho, “Analisis sentimen berbasis aspek pada ulasan aplikasi KAI Access menggunakan metode Support Vector Machine,” J. Pendidik. Teknol. Inf., vol. 6, no. 1, pp. 1–10, 2023, doi: 10.37792/jukanti.v6i1.836.
A. Mudya Yolanda and R. Tri Mulya, “Implementasi Metode Support Vector Machine untuk Analisis Sentimen pada Ulasan Aplikasi Sayurbox di Google Play Store,” VARIANSI J. Stat. Its Appl. Teach. Res., vol. 6, no. 2, pp. 76–83, 2024, doi: 10.35580/variansiunm258.
I. S. K. Idris, Y. A. Mustofa, and Irvan, “Analisis Sentimen Terhadap Penggunaan Aplikasi Shopee Mengunakan Algoritma Support Vector Machine (SVM),” JJEEEJambura J. Electr. Electron. Eng., vol. 5, no. 1, pp. 32–35, Jan. 2023, doi: 10.37905/jjeee.v5i1.16830.
V. Fitriyana, L. Hakim, D. C. R. Novitasari, and A. H. Asyhar, “Analisis Sentimen Ulasan Aplikasi Jamsostek Mobile Menggunakan Metode Support Vector Machine,” J. Buana Inform., vol. 14, no. 1, pp. 40–49, 2023, doi: 10.24002/jbi.v14i01.6909.
S. Delimasari and K. Kusrini, “Komparasi Algoritma Machine Learning Untuk Menganalisis Sentimen Ulasan Pada Aplikasi Digital Korlantas Polri,” G-Tech J. Teknol. Terap., vol. 8, no. 4, pp. 2411–2419, Oct. 2024, doi: 10.70609/gtech.v8i4.5089.
Tinaliah and T. Elizabeth, “Analisis Sentimen Ulasan Aplikasi PrimaKu Menggunakan Metode Support Vector Machine,” J. Tek. Inform. dan Sist. Inf., vol. 9, no. 4, pp. 3436–3442, 2022, doi: 10.35957/jatisi.v9i4.3586.
R. Ridwan, E. H. Hermaliani, and M. Ernawati, “Penerapan: Penerapan Metode SMOTE Untuk Mengatasi Imbalanced Data Pada Klasifikasi Ujaran Kebencian,” Comput. Sci., vol. 4, no. 1, pp. 80–88, 2024, doi: 10.31294/coscience.v4i1.2990.
S. P. Azzahra, Y. A. Apriyanto, and A. Wijaya, “Analisis Sentimen Ulasan Aplikasi DeepL Pada Google Play Dengan Metode Support Vector Machine (SVM),” JUSINJurnal Sist. Inf., vol. 4, no. 2, pp. 59–66, Dec. 2023, doi: 10.32546/jusin.v4i2.2368.
E. M. O. N. Haryanto, A. K. A. Estetikha, and R. A. Setiawan, “Implementasi SMOTE Untuk Mengatasi Imbalanced Data Pada Sentimen Analisis Sentimen Hotel di Nusa Tenggara Barat Dengan Menggunakan Algoritma SVM,” J. Inf. Interaktif, vol. 7, no. 1, pp. 16–20, 2022.
F. R. Lumbanraja, E. C. L. Gaol, D. A. Shofiana, and A. Junaidi, “Implementasi SMOTE dan Support Vector Machine Pada Klasifikasi Data Tidak Seimbang Metilasi Arginin,” J. Pepadun, vol. 5, no. 1, pp. 27–37, 2024, doi: 10.23960/pepadun.v5i1.209.
S. OKFALISA, LESTARI HANDAYANI1, DINDA JUWITA P., MUHAMMAD AFFANDES, S. S .M. FAUZI, “Coronary Heart Disease Using Support Vector Machine,” J. Eng. Sci. Technol., vol. 16, no. 2, pp. 1370–1385, 2021.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Penerapan Support Vector Machine Dengan Smote Untuk Klasifikasi Sentimen Pada Data Ulasan Aplikasi Trading View
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2025 Muhammad Badri, Elin Haerani, Fadhilah Syafria, Okfalisa, Lola Oktavia
This work is licensed under a Creative Commons Attribution 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 Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment 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 acknowledgment 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 (Refer to The Effect of Open Access).
