Analisis Klasifikasi Sentimen Neobank: Perbandingan Konfigurasi N-Gram pada TF-IDF Menggunakan Naive Bayes dan SVM
-
Fatha Amin Mujtahid
*
Universitas Semarang, Semarang,
Indonesia
- Badroe Zaman Universitas Semarang, Semarang, Indonesia
- Galet Guntoro Aji Universitas Semarang, Semarang, Indonesia (*) Corresponding Author
Abstract
The increasing number of Neobank users in Indonesia has led to a growth in user reviews on the Google Play Store, which can be utilized to assess service satisfaction and user experience. Manual analysis of these reviews is inefficient, prompting the use of automated machine learning approaches. This study evaluates the effect of N-Gram configurations in TF-IDF feature extraction on the performance of sentiment classification of Neobank reviews using Naive Bayes (NB) and Support Vector Machine (SVM). The dataset consists of 3,798 reviews, preprocessed from 5,000 initial entries collected from Google Play Store Indonesia, with 2,385 positive and 1,413 negative reviews labeled based on star ratings. Data were split using stratified five-fold cross-validation to ensure balanced class proportions in each fold. Features were extracted with TF-IDF using three N-Gram configurations: unigram, bigram, and unigram+bigram. Results indicate that N-Gram configuration significantly affects the performance of both models. NB achieved the highest accuracy with unigram (87.65%), while SVM performed best with unigram+bigram (88.61% accuracy and 88.22% F1-score). Bigram consistently yielded the lowest performance due to short and informal reviews producing sparser features. This study concludes that N-Gram selection should align with algorithm characteristics, and SVM with unigram+bigram is the most effective approach for sentiment classification of Neobank reviews in Indonesia.
Downloads
References
Adyatma, A. D., Afuan, L., & Maryanto, E. (2023). The Effect Of Unigram And Bigram In The Naïve Bayes Multinomial For Analyzing Of Comment Sentiment Of Gojek Application In Google Play Store. Jurnal Teknik Informatika (JUTIF), 4(6), 1535–1540. https://doi.org/10.52436/1.jutif.2023.4.6.1310
Arifin, M. N., Hamzah, A., Huda, M. A., & Hasanah, N. (2025). Analysis of Google Play Store User Sentiment Towards Application X Using the SVM Algorithm. Brilliance, 5(1), 249–258. https://doi.org/10.47709/brilliance.v5i1.6024
Bimantara, M. D., & Zufria, I. (2024). Text Mining Sentiment Analysis On Mobile Banking Application Reviews Using TF-IDF Method With Natural Language Processing Approach. JINAV: Journal of Information and Visualization, 5(1), 115–123. https://doi.org/https://doi.org/10.35877/454RI.jinav2772
Enjelia, L., Cahyana, Y., & Wahiddin, D. (2025). Comparison of K-Nearest Neighbors and Naive Bayes Classifier Algorithms in Sentiment Analysis of 2024 Election in Twitter ( X ). Journal of Applied Informatics and Computing (JAIC), 9(3), 946–954. https://doi.org/10.30871/jaic.v9i3.9593
Hadi, K., & Utami, E. (2024). Analysis of K-NN with the Integration of Bag of Words , TF-IDF , and N-Grams for Hate Speech Classification on Twitter. JUITA: Jurnal Informatika, 12(2), 289–298. https://doi.org/10.30595/juita.v12i2.23829
Helmi, A. Y., & Kristianto, A. H. (2024). Sistem RGEC Dalam Analisis Tingkat Kesehatan Bank Digital Yang Terdaftar Di BEI Periode 2019-2022. MARGIN ECO: Jurnal Ekonomi Dan Perkembangan Bisnis, 8(1), 75–98. https://doi.org/10.32764/margin.v8i1.4511
Kadek, N., Puspita, F., Sudipa, I. G. I., Sunarya, I. W., Wayan, N., & Kusuma, J. (2025). Sentiment Analysis of Roblox Game Reviews on Google Play Store Using Lexicon-SVM Integration. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 9(4), 1863–1876. https://doi.org/10.33395/sinkron.v9i4.15272
Kusnawi, Rahardi, M., & Pandiangan, V. D. (2023). Sentiment Analysis of Neobank Digital Banking Using Support Vector Machine Algorithm in Indonesia. JOIV, 7(June), 377–383. https://doi.org/10.30630/joiv.7.2.1652
Manjula, S., Rajini, N. H., & Chokkanathan, K. (2025). Enhanced chronic kidney disease detection using XGBoost with improved brainstorm optimization for hyperparameter tuning. Discover Applied Sciences, 7, 1181. https://doi.org/10.1007/s42452-025-07633-7
Nurhayati, Tanti, L., & Triandi, B. (2026). Optimasi Support Vector Machine Menggunakan Particle Swarm Optimization pada Analisis Sentimen Program Efisiensi Anggaran Pemerintah. Jurnal Minfo Polgan (JMP), 15(1), 130–144. https://doi.org/https://doi.org/10.33395/jmp.v15i1.15929
Özyirmidokuz, E. K., & Elmas, B. M. (2025). AI-Based Sentiment Analysis of E-Commerce Customer Feedback : A Bilingual Parallel Study on the Fast Food Industry in Turkish and English. Journal of Theoritical and Applied Electronic Commerce Research, 20, 294. https://doi.org/10.3390/jtaer20040294
Prayudya, D. R., Ikhwan, I., Nugroho, T., & Ramdiania, R. G. N. (2025). Comparing Neo and Traditional Banking Efficiency : A Three-Stage DEA Analysis in Indonesia. Jurnal Ekonomi Malaysia, 59(December 2024). https://doi.org/http://dx.doi.org/10.17576/JEM-2025-5901-5 Comparing
Putra, K. T., Hariyadi, M. A., & Crysdian, C. (2023). Perbandingan Feature Extraction Tf-Idf Dan Bow Untuk Analisis Sentimen Berbasis SVM. Jurnal Cahaya Mandalika, 3(2), 1449–1463. https://www.ojs.cahayamandalika.com/index.php/jcm/article/view/2292
Putri, D. W., & Soeleman, M. A. (2026). Penerapan Algoritma Naïve Bayes Terhadap Sentimen Ulasan Produk Skincare Pada E-Commerce Shopee. Building of Informatics, Technology and Science (BITS), 7(4), 2218–2228. https://doi.org/10.47065/bits.v7i4.9209
Raharjo, R. A., Sunarya, I. M. G., & Divayana, D. G. H. (2022). Perbandingan Metode Naïve Bayes Classifier Dan Support Vector Machine Pada Kasus Analisis Sentimen Terhadap Data Vaksin. Jurnal Ilmiah Elektronika Dan Komputer, 15(2), 456–464. https://doi.org/10.51903/elkom.v15i2.918
Rahmaliyadi, V., & Maridjan, M. M. (2025). Sentiment Analysis of Indonesian-Language Plantix Application Reviews for Plant Disease Diagnosis Using Naive Bayes Methods. Journal of Intelligent Systems Technology and Informatics, 1(2), 62–66. https://doi.org/10.64878/jistics.v1i2.12
Rahmatulloh, F., Sumarwan, U., Hartoyo, & Sartono, B. (2024). Unveiling Factors Influencing Neobanking Adoption With An Extended UTAUT-3 Model To Improve Neobank Marketing Strategy. International Journal Of Economics And Finance Studies, 16(03), 203–228. https://doi.org/10.34109/ijefs.202416310
Setiawan, A., & Hasan, F. N. (2025). Analisis Sentimen Tanggapan Pengguna Aplikasi Bale By Btn Menggunakan Metode Support Vector Machine ( SVM ). STORAGE – Jurnal Ilmiah Teknik Dan Ilmu Komputer, 4(4), 315–326. https://doi.org/10.55123/storage.v4i4.6469
Ulgasesa, R., Negara, A. B. P., & Tursina. (2022). Pengaruh Stemming Terhadap Performa Klasifikasi Sentimen Masyarakat Tentang Kebijakan New Normal. JUSTIN : Jurnal Sistem Dan Teknologi Informasi, 10(3), 286–293. https://doi.org/10.26418/justin.v10i3.53880
Zafira, Z. T., Tania, K. D., & Sari, W. K. (2025). Sentiment-Based Knowledge Discovery of Wondr by BNI App Reviews Using SVM , KNN , and Naive Bayes for CRM Enhancement. Journal of Applied Informatics and Computing (JAIC), 9(5), 2498–2508. https://doi.org/10.30871/jaic.v9i5.10323
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Klasifikasi Sentimen Neobank: Perbandingan Konfigurasi N-Gram pada TF-IDF Menggunakan Naive Bayes dan SVM
Pages: 2375-2383
Copyright (c) 2026 Fatha Amin Mujtahid, Badroe Zaman, Galet Guntoro Aji
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).
