Sentimen Analisis dengan Long Short-Term Memory dan Synthetic Minority Over Sampling Technic Pada Aplikasi Digital Perbankan

Ali Ahmad; Windu Gata; Supriadi Panggabean

doi:10.35870/jtik.v8i4.2320

PDF

DOI:

https://doi.org/10.35870/jtik.v8i4.2320

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

KITA Institute or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Ali Ahmad ⁽¹⁾ , Windu Gata ⁽²⁾ , Supriadi Panggabean ⁽³⁾

Published: Oct 1, 2024

Show Affiliations

⁽¹⁾ Ali Ahmad:

Program Studi Ilmu Komputer, Fakultas Ilmu Komputer, Universitas Nusa Mandiri, Kota Jakarta Pusat, Daerah Khusus Ibukota Jakarta, Indonesia

⁽²⁾ Windu Gata:

Program Studi Ilmu Komputer, Fakultas Ilmu Komputer, Universitas Nusa Mandiri, Kota Jakarta Pusat, Daerah Khusus Ibukota Jakarta, Indonesia

⁽³⁾ Supriadi Panggabean:

Program Studi Ilmu Komputer, Fakultas Ilmu Komputer, Universitas Nusa Mandiri, Kota Jakarta Pusat, Daerah Khusus Ibukota Jakarta, Indonesia

Abstract:

In recent years, we have witnessed significant growth in digital banking transactions, supported by technological advancements. According to the latest data from the FinTech Association of Indonesia, digital banking transactions in Indonesia have increased by 35% from the previous year. In this context, the development of digital banking applications becomes increasingly important. However, to ensure the quality and success of these applications, feedback from users is crucial. One technique used by banks is sentiment analysis to gather feedback on their digital applications. This research aims to analyze user sentiment for two banking applications, DbankPro and M-BCA, through reviews on the Google Playstore. The method used is CRISP-DM, implementing the "Imbalance Data Handling with SMOTE" technique and LSTM model. The test results show the accuracy of sentiment analysis for M-BCA is 91.07%, while for DbankPro it is 89.82%. The implications of this research emphasize the importance of paying attention to user feedback in the development of digital banking applications to enhance their quality and meet user expectations

Keywords:

Sentiment Analysys, Text Mining, LSTM, Class Imbalance

Total Downloads Artikel Last 1 Year

Download data is not yet available.

How to Cite

Ahmad, A., Gata, W., & Panggabean, S. (2024). Sentimen Analisis dengan Long Short-Term Memory dan Synthetic Minority Over Sampling Technic Pada Aplikasi Digital Perbankan. Jurnal JTIK (Jurnal Teknologi Informasi Dan Komunikasi), 8(4), 973–984. https://doi.org/10.35870/jtik.v8i4.2320

Author Biographies

Ali Ahmad, Universitas Nusa Mandiri

Program Studi Ilmu Komputer, Fakultas Ilmu Komputer, Universitas Nusa Mandiri, Kota Jakarta Pusat, Daerah Khusus Ibukota Jakarta, Indonesia

Windu Gata, Universitas Nusa Mandiri

Program Studi Ilmu Komputer, Fakultas Ilmu Komputer, Universitas Nusa Mandiri, Kota Jakarta Pusat, Daerah Khusus Ibukota Jakarta, Indonesia

Supriadi Panggabean, Universitas Nusa Mandiri

Program Studi Ilmu Komputer, Fakultas Ilmu Komputer, Universitas Nusa Mandiri, Kota Jakarta Pusat, Daerah Khusus Ibukota Jakarta, Indonesia

References

Fauziyyah, A. K. (2020). Analisis sentimen pandemi Covid19 pada streaming Twitter dengan text mining Python. Jurnal Ilmiah SINUS, 18(2), 31-42. DOI: http://dx.doi.org/10.30646/sinus.v18i2.491.

Kusnawi, K., & Rahardi, M. (2023). Sentiment Analysis of Neobank Digital Banking using Support Vector Machine Algorithm in Indonesia. JOIV: International Journal on Informatics Visualization, 7(2), 377-383. DOI: http://dx.doi.org/10.30630/joiv.7.2.1652.

Sari, W. F., Rahim, R., & Adrianto, F. (2023). Analisis Sentiment Review Pengguna BCA Mobile Menggunakan Teks Mining. Cakrawala Repositori IMWI, 6(2), 981-987. DOI: https://doi.org/10.52851/cakrawala.v6i2.295.

Gupta, A., & Kamthania, D. (2021, April). Study of Sentiment on Google Play Store Applications. In Proceedings of the International Conference on Innovative Computing & Communication (ICICC).

Rahman, M. Z., Sari, Y. A., & Yudistira, N. (2021). Analisis Sentimen Tweet COVID-19 menggunakan Word Embedding dan Metode Long Short-Term Memory (LSTM). Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 5(11), 5120-5127.

Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321-357. DOI: https://doi.org/10.1613/jair.953.

Ulfa, M. A., Irmawati, B., & Husodo, A. Y. (2018). Twitter Sentiment Analysis using Na¨ ive Bayes Classifier with Mutual Information Feature Selection. Journal of Computer Science and Informatics Engineering (J-Cosine), 2(2), 106-111.

Suhaeni, C., & Yong, H. S. (2023). Mitigating Class Imbalance in Sentiment Analysis through GPT-3-Generated Synthetic Sentences. Applied Sciences, 13(17), 9766. DOI: https://doi.org/10.3390/app13179766.

Sudriani, Y., Ridwansyah, I., & A Rustini, H. (2019, July). Long short term memory (LSTM) recurrent neural network (RNN) for discharge level prediction and forecast in Cimandiri river, Indonesia. In IOP Conference series: Earth and environmental science (Vol. 299, p. 012037). IOP Publishing. DOI 10.1088/1755-1315/299/1/012037.

Witantoa, K. S., ERa, N. A. S., Karyawatia, A. E., Arya, I. G. A. G., Kadyanana, I., & Astutia, L. G. (2022). Implementasi LSTM pada Analisis Sentimen Review Film Menggunakan Adam dan RMSprop Optimizer. Jurnal Elektronik Ilmu Komputer Udayana p-ISSN, 2301, 5373.

Cahyadi, R., Damayanti, A., & Aryadani, D. (2020). Recurrent neural network (rnn) dengan long short term memory (lstm) untuk analisis sentimen data instagram. JIKO (Jurnal Informatika dan Komputer), 5(1), 1-9. DOI: http://dx.doi.org/10.26798/jiko.v5i1.407.

Yan, H., Ma, M., Wu, Y., Fan, H., & Dong, C. (2022). Overview and analysis of the text mining applications in the construction industry. Heliyon, 8(12). DOI:https://doi.org/10.1016/j.heliyon.2022.e12088.

Widowati, T. T., & Sadikin, M. (2020). Analisis Sentimen Twitter terhadap Tokoh Publik dengan Algoritma Naive Bayes dan Support Vector Machine. Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer, 11(2), 626-636. DOI: https://doi.org/10.24176/simet.v11i2.4568.

Permana, Y., & Emarilis, A. (2021, March). Stemming analysis indonesian language news text with Porter algorithm. In Journal of Physics: Conference Series (Vol. 1845, No. 1, p. 012019). IOP Publishing. DOI 10.1088/1742-6596/1845/1/012019.

Sarica, S., & Luo, J. (2021). Stopwords in technical language processing. Plos one, 16(8), e0254937. DOI: https://doi.org/10.1371/journal.pone.0254937.

Rojas‐Barahona, L. M. (2016). Deep learning for sentiment analysis. Language and Linguistics Compass, 10(12), 701-719. DOI: https://doi.org/10.1111/lnc3.12228.

Sailasya, G., & Kumari, G. L. A. (2021). Analyzing the performance of stroke prediction using ML classification algorithms. International Journal of Advanced Computer Science and Applications, 12(6).

Halim, A. M., Dwifebri, M., & Nhita, F. (2023). Handling Imbalanced Data Sets Using SMOTE and ADASYN to Improve Classification Performance of Ecoli Data Sets. Building of Informatics, Technology and Science (BITS), 5(1), 246-253. DOI: https://doi.org/10.47065/bits.v5i1.3647.

Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi)