Klasifikasi Sentimen Ulasan Pengguna Aplikasi Paylater di Indonesia Menggunakan Mesin Pembelajaran

Muhammad Ardi Hermansyah; Muhammad Arifin; Pratomo Setiaji

doi:10.36080/idealis.v9i2.3814

Authors

Muhammad Ardi Hermansyah Sistem Informasi, Fakultas Teknik, Universitas Muria Kudus, Kudus, Indonesia
Muhammad Arifin Sistem Informasi, Fakultas Teknik, Universitas Muria Kudus, Kudus, Indonesia
Pratomo Setiaji Sistem Informasi, Fakultas Teknik, Universitas Muria Kudus, Kudus, Indonesia

DOI:

https://doi.org/10.36080/idealis.v9i2.3814

Keywords:

Sentiment Analysis, Paylater, TF-IDF, Logistic Regression, Random Forest, SMOTE

Abstract

The increasing use of paylater services in various regions of Indonesia has given rise to a large collection of user reviews that contain meaningful information about how users evaluate and perceive the experience of using the service. This research focuses on the classification of sentiment contained in paylater app reviews using two machine learning approaches, namely Random Forest and Logistic Regression, which are tested both with and without the application of the Synthetic Minority Oversampling Technique (SMOTE) to address class inequality. Review information is obtained from the Google Play Store and goes through a series of initial steps involving text cleaning, case processing, standardization of non-standard words, splitting sentences into tokens, removing meaningless words, and also stemming. Subsequent characteristic extraction is carried out using the TF-IDF method (Term Frequency-Inverse Document Frequency), before the data is divided into training and testing sets using three split configurations: 80:20, 70:30, and 60:40, to evaluate model consistency across varying training data sizes. The 80:20 split consistently produced the highest performance across all models. The results of all tested configurations, the combination of Logistic Regression with SMOTE provided the best results, achieving 88.38% accuracy, 88.37% precision, 88.38% recall, and 88.37% F1-score. Unlike previous studies that analyzed sentiment from a single paylater application using a single algorithm without class balancing, this study contributes by simultaneously collecting data from three major paylater applications and empirically comparing the effect of SMOTE on two algorithms across three data split configurations, providing a more comprehensive and generalizable benchmark for paylater sentiment classification in Indonesia. This finding indicates that the application of SMOTE also strengthens the model's performance by addressing the imbalance between sentiment classes, while Logistic Regression is proven to be able to recognize patterns related to sentiment in review text. In general, this study shows that combination of TF-IDF, Logistic Regression, and SMOTE builds an effective system for classifying sentiment in paylater application reviews.

Downloads

Download data is not yet available.

References

[1] A. Koswara, E. S. Soegoto, R. Wahdiniwaty, M. Bachtiar, and I. D. Sumitra, “Persaingan PayLater di Indonesia: Analisis pasar dan peramalan minat konsumen berbasis data science,” J. Salingka Nagari, vol. 04, no. 2, pp. 254–270, 2025. [Online]. Available: https://jsn.ppj.unp.ac.id/index.php/jsn/article/view/341

[2] F. J. Wahidna and P. Nerisafitra, “Analisis sentimen pengguna sistem Pay Later menggunakan Support Vector Machine metode pembobotan lexicon,” JINACS (Journal Informatics Comput. Sci.), vol. 04, no. 03, pp. 334–343, 2023, doi: 10.26740/jinacs.v4n03.p334-343.

[3] Otoritas Jasa Keuangan, “Roadmap Pengembangan dan Penguatan Perusahaan Pembiayaan 2024–2028,” Jakarta, 2024. Accessed: Jun. 28, 2026. [Online]. Available: https://www.ojk.go.id/id/berita-dan-kegiatan/info-terkini/Documents/Pages/Roadmap-Pengembangan-dan-Penguatan-Perusahaan-Pembiayaan-2024-2028/Roadmap Pengembangan dan Penguatan Perusahaan Pembiayaan 2024-2028_Final.pdf

[4] A. I. Rahmana, “Penyaluran pembiayaan buy now pay later tembus Rp 36,24 triliun per Februari 2025.” Accessed: Jun. 28, 2026. [Online]. Available: https://keuangan.kontan.co.id/news/penyaluran-pembiayaan-buy-now-pay-later-tembus-rp-3624-triliun-per-februari-2025

[5] Y. Tandiarny, Afifah, and Y. Saharaeni, “Analisis tingkat kepuasan pengguna Shopee Paylater menggunakan metode User Experience Questionare,” J. Ilmu Komput. KHARISMA Tech, vol. 29, no. 01, pp. 1–14, 2025, doi: 10.55645/kharismatech.v20i1.505.

[6] I. Ristiana and Mutmainah, “Analisis sentimen bencana banjir Sumatera menggunakan TF-IDF dan Logistic Regression,” J. Sist. Inf. DAN Teknol. ( S I N T E K ), vol. 6, no. 1, pp. 57–65, 2021, doi: 10.56995/sintek.v6i1.239.

[7] T. F. Basar, D. E. Ratnawati, and I. Arwani, “Analisis sentimen pengguna Twitter terhadap pembayaran cashless menggunakan Shopeepay dengan algoritma Random Forest,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 6, no. 3, pp. 1426–1433, 2022. [Online]. Available: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/10830

[8] S. G. Wijaya and Suharyadi, “Analisis sentimen pengguna Twitter terhadap kebijakan royalti restoran dan kafe dengan Multinomial Naive Bayes,” Idealis Indones. J. Inf. Syst., vol. 9, no. 1, pp. 49–58, 2026, doi: 10.36080/idealis.v9i1.3698.

[9] A. Safira and F. N. Hasan, “Analisis sentimen masyarakat terhadap Paylater menggunakan metode Naive Bayes Classifier,” Zo. J. Sist. Inf., vol. 5, no. 1, pp. 59–70, 2023, doi: 10.31849/zn.v5i1.12856.

[10] R. Rizaldi and R. Aryanti, “Analisis sentimen pengguna terhadap aplikasi Indodana di Google Play Store menggunakan metode Naive Bayes Classifier,” J. Informatics Manag. Inf. Technol., vol. 3, no. 4, pp. 98–105, 2024, doi: 10.47065/jimat.v4i3.400.

[11] S. F. Kadir and A. Fairuzabadi, “Analisis sentimen ulasan Shopee di Google Play dengan TF-IDF dan Logistic Regression,” J. Artif. Intell. Digit. Bus., vol. 4, no. 2, pp. 7940–7945, 2025, doi: 10.31004/riggs.v4i2.2850.

[12] M. Sahrul and Afiyati, “Sentimen analisis pada ulasan aplikasi Indodana di Google Play Store menggunakan algoritma Logistic Regression, Naïve Bayes dan Support Vector Machine,” J. Nas. Teknol. Komput., vol. 5, no. 3, pp. 136–147, 2025, doi: 10.61306/jnastek.v5i3.194.

[13] M. F. Rahmatullah, P. L. Lokapitasari Belluano, and H. Darwis, “Analisis sentimen review aplikasi di Google Play Store menggunakan Random Forest,” LINIER Lit. Inform. dan Komput., vol. 2, no. 3, pp. 380–389, 2025, doi: 10.33096/linier.v2i3.3149.

[14] D. Rifaldi, A. Fadhil, and Herman, “Teknik preprocessing pada Text Mining menggunakan Tweet ‘Mental Health,’” Decod. J. Pendidik. Teknol. Inf. ISSN, vol. 3, no. 2, pp. 161–171, 2023, doi: 10.51454/decode.v3i2.131.

[15] N. Garg and K. Sharma, “Text pre-processing of multilingual for sentiment analysis based on social network data,” Int. J. Electr. Comput. Eng., vol. 12, no. 1, pp. 776–784, 2022, doi: 10.11591/ijece.v12i1.pp776-784.

[16] R. Kalaivani and R. Marivendan, “The effect of stop word removal and stemming in datapreprocessing,” Ann. Rom. Soc. Cell Biol., vol. 25, no. 6, pp. 739–746, 2021. [Online]. Available: https://www.proquest.com/openview/7d09e95c5e0d540c8765cf0d41a7ce39/1?pq-origsite=gscholar&cbl=2031963

[17] K. H, Y. Desnelita, and D. Oktarina, “Analisis sentimen terhadap ulasan aplikasi IKD di Play Store menggunakan Random Forest,” J. Nas. Tek. Elektro dan Teknol. Inf., vol. 14, no. 3, pp. 171–180, 2025, doi: 10.22146/jnteti.v14i3.20473.

[18] H. Wang, B. Liu, Y. Yang, and T. Li, “Learning with noisy labels for sentence-level sentiment classification,” Inf. Process. Manag., vol. 60, no. 2, pp. 6286–6292, 2023, doi: 10.18653/v1/D19-1655.

[19] O. I. Gifari, M. Adha, I. R. Hendrawan, and F. F. S. Durrand, “Analisis sentimen review film menggunakan TF-IDF dan Support Vector Machine,” JIFOTECH (Journal Inf. Technol.), vol. 2, no. 1, pp. 36–40, 2022, doi: 10.46229/jifotech.v2i1.330.

[20] N. Nurdiansyah, F. S. Febriyan, Z. G. D. Amanta, D. A. Saputra, and W. M. Baihaqi, “Analisis kesehatan mental untuk mencegah gangguan mental pada mahasiswa menggunakan algoritma K-Nearest Neighbor (K-NN) dan Random Forest,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 5, no. 1, pp. 1–10, 2025, doi: 10.57152/malcom.v5i1.1537.

[21] C. Cahyaningtyas, Y. Nataliani, and I. R. Widiasari, “Analisis sentimen pada rating aplikasi Shopee menggunakan metode Decision Tree berbasis SMOTE,” AITI J. Teknol. Inf., vol. 18, no. 2, pp. 173–184, 2021, doi: 10.24246/aiti.v18i2.173-184.

[22] A. Fathkudin, F. A. Artanto, N. A. Safli, and D. Wibowo, “Decision Tree berbasis SMOTE dalam analisis sentimen penggunaan artificial intelligence untuk skripsi,” Remik Ris. dan E-Jurnal Manaj. Inform. Komput., vol. 8, no. 2, pp. 494–505, 2024, doi: 10.33395/remik.v8i2.13531.

[23] A. Khaidar, “Analisis sentimen di Instagram terhadap menteri keuangan Purbaya Yudhi Sadewa menggunakan metode Logistic Regression,” JITET (Jurnal Inform. dan Tek. Elektro Ter.), vol. 13, no. 3, pp. 1674–1683, 2025, doi: 10.23960/jitet.v13i3S1.8002.

[24] N. A. Hapsari and A. D. Indriyanti, “Analisis sentimen pada aplikasi dompet digital menggunakan algoritma Random Forest,” J. Emerg. Inf. Syst. Bus. Intell., vol. 4, no. 3, pp. 186–192, 2023, doi: 10.26740/jeisbi.v4i3.55696.

[25] N. Hidayah and Dodiman, “Implementasi algoritma Multinomial Naïve Bayes, TF-IDF dan Confusion Matrix dalam pengklasifikasian saran monitoring dan evaluasi mahasiswa terhadap dosen Teknik Informatika Universitas Dayanu Ikhsanuddin,” J. Akad. Pendidik. Mat., vol. 10, no. 1, pp. 8–15, 2024, doi: 10.55340/japm.v10i1.1491.