Text Mining Sentiment Analysis on Mobile Banking Application Reviews using TF-IDF Method with Natural Language Processing Approach

Muhammad Dhuha  Bimantara; Ilka Zufria

doi:10.35877/454RI.jinav2772

Muhammad Dhuha Bimantara Departement of Computer Science, Faculty of Science and Tecnology, Universitas Islam Negeri Sumatera Utara, Medan, 20236, Indonesia (ID)
Ilka Zufria Departement of Computer Science, Faculty of Science and Tecnology, Universitas Islam Negeri Sumatera Utara, Medan, 20236, Indonesia (ID)

https://doi.org/10.35877/454RI.jinav2772

Keywords: Text Mining, Natural Languange Processing, Sentiment Analysis

Viewed = 0 time(s)

Abstract

As part of its efforts to improve digital banking services, PT Bank Rakyat Indonesia (Persero) Tbk (BRI) has launched a mobile banking application called BRImo. This move is in line with the global trend where financial institutions are increasingly focusing on digitalization to meet the evolving needs of customers who demand faster and more efficient accessibility to banking services. BRImo comes as an innovative solution to provide a better banking experience to BRI customers. This research was conducted to find out the reviews of the BRImo application on the App markets google playstore, In BRImo mobile banking's efforts to remain competitive with other mobile banking applications, understanding positive and negative reviews from users is very important. The fundamental issue that must be addressed is how to analyze positive reviews to strengthen the advantages of the BRImo app and identify negative reviews to address weaknesses that may hinder its competitiveness. This research was conducted to find out the reviews of the BRImo application on the App markets google playstore, In BRImo mobile banking's efforts to remain competitive with other mobile banking applications, understanding positive and negative reviews from users is very important. The method used in the calculation is TF-IDF and NLP approach and the calculation of SVM algorithm is trained using training data. The calculation results show that the model has an accuracy of 92%. or Precision Score of about 92%, Recall Score has 100% and F1 Score has 0.95 or approximately 95%.

References

Asri, M. F. N., Widodo, C. E., & Sediyono, E. (2023). Trend Analysis of The Effect of LQ45 Stocks on Stock Price Index Fluctuations using The C4.5 Algorithm with Correlation-Based Feature Selection and Information Gain.

Asri, Y., Suliyanti, W. N., Kuswardani, D., & Fajri, M. (2022). Pelabelan Otomatis Lexicon Vader dan Klasifikasi Naive Bayes dalam menganalisis sentimen data ulasan PLN Mobile: Analisis Sentimen. PETIR, 15(2), 264–275. https://doi.org/10.33322/petir.v15i2.1733

Darwis, D., Pratiwi, E. S., & Pasaribu, A. F. O. (2020). Penerapan Algoritma Svm Untuk Analisis Sentimen Pada Data Twitter Komisi Pemberantasan Korupsi Republik Indonesia. Edutic - Scientific Journal of Informatics Education, 7(1). https://doi.org/10.21107/edutic.v7i1.8779

Firdaus, A., & Firdaus, W. I. (2021). Text Mining Dan Pola Algoritma Dalam Penyelesaian Masalah Informasi: (Sebuah Ulasan). 13(1).

Friska Aditia Indriyani, Ahmad Fauzi, & Sutan Faisal. (2023). Analisis sentimen aplikasi tiktok menggunakan algoritma naïve bayes dan support vector machine. TEKNOSAINS : Jurnal Sains, Teknologi dan Informatika, 10(2), 176–184. https://doi.org/10.37373/tekno.v10i2.419

Furqan, M., Sriani, S., & Shidqi, M. N. (2023). Chatbot Telegram Menggunakan Natural Language Processing. Walisongo Journal of Information Technology, 5(1), 15–26. https://doi.org/10.21580/wjit.2023.5.1.14793

Hilda Kusumahadi, S., Junaedi, H., & Santoso, J. (2019). Klasifikasi Helpdesk Menggunakan Metode Support Vector Machine. Jurnal Informatika: Jurnal Pengembangan IT, 4(1), 54–60. https://doi.org/10.30591/jpit.v4i1.1125

Ikhsan, M., & Kurniawan, R. (2023). Penerapan Text Mining pada Sistem Rekomendasi Pembimbing Skripsi Mahasiswa Menggunakan Algoritma Naïve Bayes Classifier. Indonesian Journal of Computer Science, 12(6).

Kurniawan R, R., & Zufria, I. (2022). Penerapan Text Mining Pada Sistem Penyeleksian Judul Skripsi Menggunakan Algoritma Latent Dirichlet Allocation(LDA). Indonesian Journal of Computer Science, 11(3). https://doi.org/10.33022/ijcs.v11i3.3120

Lubis, A. H., Darta, A., & Filla, S. U. F. (2022). Islamophobia Sentiment Classifcation Using Support Vector Machine. J. Intell. Comput. Health Inform, 3. https://doi.org/10.26714/jichi.v3i2.11179

Muktafin, E. H., Kusrini, K., & Luthfi, E. T. (2020). Analisis Sentimen pada Ulasan Pembelian Produk di Marketplace Shopee Menggunakan Pendekatan Natural Language Processing. Jurnal Eksplora Informatika, 10(1), 32–42. https://doi.org/10.30864/eksplora.v10i1.390

Nofandi, A., Setiawan, N. Y., & Brata, D. W. (2023). Analisis Sentimen Ulasan Pelanggan dengan Metode Support Vector Machine (SVM) untuk Peningkatan Kualitas Layanan pada Restoran Warung Wareg. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 7(1), 458–466.

Ramlan, R., Satyahadewi, N., & Andani, W. (2023). Analisis Sentimen Pengguna Twitter Menggunakan Support Vector Machine Pada Kasus Kenaikan Harga BBM. Jambura Journal of Mathematics, 5(2), 431–445. https://doi.org/10.34312/jjom.v5i2.20860

Rifaldi, D., Abdul Fadlil, & Herman. (2023). Teknik Preprocessing Pada Text Mining Menggunakan Data Tweet “Mental Health.” Decode: Jurnal Pendidikan Teknologi Informasi, 3(2), 161–171. https://doi.org/10.51454/decode.v3i2.131

Trianto, R. B., Triyono, A., & Arum, D. M. P. (2020). Klasifikasi Rating Otomatis pada Dokumen Teks Ulasan Produk Elektronik Menggunakan Metode N-gram dan Naïve Bayes. Jurnal Informatika Universitas Pamulang, 5(3), 295. https://doi.org/10.32493/informatika.v5i3.6110

Umar, R., Sunardi, & Ardiansyah Nur, M. (2022). Penerapan Algoritma Support Vector Machine Pada Analisis Sentimen Hashtag Twitter. JURIKOM (Jurnal Riset Komputer), 9, 1607–1613.