Sentiment Analysis of Simobi Plus Mobile Application Using Naïve Bayes Classification

Authors

  • Stevan Hamonangan Hardi Satya Wacana Christian University, Salatiga
  • Kristoko Dwi Hartomo Satya Wacana Christian University, Salatiga

DOI:

https://doi.org/10.30865/mib.v7i3.6300

Keywords:

Simobi Plus Mobile Banking, Sentiment Analysis, Naïve Bayes Classification, Google Play Store

Abstract

Sinar Mas Bank is one of many banks operating in Indonesia. Quite a few people use Sinar Mas Bank's services as their bank of choice for their day-to-day transactions. By popular demand, Sinar Mas Bank serves users of banking services by creating an M-banking application. The M-banking application created by Bank Sinar Mas is called Simobi Plus Mobile Banking. There are already 52.3 thousand reviews regardings this application on the Google Play Store platform. Among these are positive and negative reviews from customers who use the application for their daily transactions. In reviews that use 1-5 star ratings, many people are misled by giving different ratings than the given stars. Many customers who leave 5-star app reviews, but comments on these reviews contain negative words. As a result, the application developer becomes confused because the comments given do not match the rating given by the user. Comments that are not in accordance with the rating given can involve the developer of the application to make improvements or development for the application. Therefore, Research should be conducted using techniques and analytics to categorize the user comments into several groups. This study uses sentiment analysis using the Naive Bayes method to capture positive and negative sentiments for comments on the Simobi Plus mobile banking application on the Google Play store, so that these sentiments have the appropriate value. The accuracy scores for the negative class, positive class, recall, and mood analysis are used to evaluate the test. The resulting value has an accuracy of 99%, which is almost perfect. The precision value was 100%, whereas the recall class produced a value of 98% (positive class: negative). And the AUC value is 0.980.

References

Naomi Adisty, “Mengulik Perkembangan Penggunaan Smartphone di Indonesia,†https://goodstats.id/article/mengulik-perkembangan-penggunaan-smartphone-di-indonesia-sT2LA, 5 November 2022.

Adi Ahdiat, “67% Penduduk Indonesia Punya Handphone pada 2022, Ini Sebarannya,†https://databoks.katadata.co.id/datapublish/2023/03/08/67-penduduk-indonesia-punya-handphone-pada-2022-ini-sebarannya#:~:text=Menurut%20data%20Badan%20Pusat%20Statistik,rekor%20tertinggi%20dalam%20sedekade%20terakhir, 8 Maret 2023.

M. Khoirul, U. Hayati, dan O. Nurdiawan, “ANALISIS SENTIMEN APLIKASI BRIMO PADA ULASAN PENGGUNA DI GOOGLE PLAY MENGGUNAKAN ALGORITMA NAIVE BAYES,†2023.

E. Fitri, Y. Yuliani, S. Rosyida, dan W. Gata, “Analisis Sentimen Terhadap Aplikasi Ruangguru Menggunakan Algoritma Naive Bayes, Random Forest Dan Support Vector Machine,†TRANSFORMTIKA, vol. 18, no. 1, hlm. 71–80, 2020, [Daring]. Tersedia pada: www.nusamandiri.ac.id,

A. Mittal dan S. Patidar, “Sentiment analysis on twitter data: A survey,†dalam ACM International Conference Proceeding Series, Association for Computing Machinery, Jul 2019, hlm. 91–95. doi: 10.1145/3348445.3348466.

R. Wahyudi dkk., “Analisis Sentimen pada review Aplikasi Grab di Google Play Store Menggunakan Support Vector Machine,†JURNAL INFORMATIKA, vol. 8, no. 2, 2021, [Daring]. Tersedia pada: http://ejournal.bsi.ac.id/ejurnal/index.php/ji

M. N. Akbar, N. Hasanahlmar’iyah Rusydi, M. Hasrul, dan S. Ramadhanti, “Sentiment Analysis Terhadap Review Aplikasi Maxim di Google Play Store Menggunakan Support Vector Machine (SVM),†vol. 2, no. 2, hlm. 1, 2022.

J. W. Iskandar dan Y. Nataliani, “Perbandingan Naïve Bayes, SVM, dan k-NN untuk Analisis Sentimen Gadget Berbasis Aspek,†Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 5, no. 6, hlm. 1120–1126, Des 2021, doi: 10.29207/resti.v5i6.3588.

P. S. M. Suryani, L. Linawati, dan K. O. Saputra, “Penggunaan Metode Naïve Bayes Classifier pada Analisis Sentimen Facebook Berbahasa Indonesia,†Majalah Ilmiah Teknologi Elektro, vol. 18, no. 1, hlm. 145, Mei 2019, doi: 10.24843/mite.2019.v18i01.p22.

B. Kurniadi Widodo, N. Hafifah Matondang, dan D. Sandya Prasvita, “Penerapan Algoritma Naive Bayes Untuk Analisis Sentimen Penggunaan Aplikasi Jobstreet Implementation of Naive Bayes Algorithm For Sentiment Analysis Of The Use Of Jobstreet Application,†2022.

A. V. Sudiantoro dan E. Zuliarso, ANALISIS SENTIMEN TWITTER MENGGUNAKAN TEXT MINING DENGAN ALGORITMA NAÃVE BAYES CLASSIFIER. 2018.

Ryan Mitchell, Web scraping with Python: collecting data from the modern web, 4 ed. 2018.

D. Deviacita dkk., “Implementasi Web Scraping untuk Pengambilan Data pada Situs Marketplace,†vol. 7, no. 4, 2019.

E. Fadilah, “Implementasi Metode Profile Matching Terhadap Sistem Pendukung Keputusan Penerimaan Dana Zakat pada Badan Amil Zakat Pertamina (BAZMA),†MATICS, vol. 10, no. 2, hlm. 39, Mar 2019, doi: 10.18860/mat.v10i2.5745.

V. A. Permadi, “Analisis Sentimen Menggunakan Algritma Naïve Bayes Terhadap Review Restoran di Singapura 141,†2020. [Daring]. Tersedia pada: https://www.kaggle.com/hj5992/restaurantreviews

Anirudh Aggarwal, “Introduction To Google Colab,†https://medium.com/@animaze97/introduction-to-google-colab-9b2e28fe691a, 20 Maret 2018.

T. Krisdiyanto, E. Maricha, dan O. Nurharyanto, “Analisis Sentimen Opini Masyarakat Indonesia Terhadap Kebijakan PPKM pada Media Sosial Twitter Menggunakan Naïve Bayes Clasifiers,†Jurnal CoreIT, vol. 7, no. 1, 2021.

K. Ivana Ruslim dan P. Pandu Adikara, “Analisis Sentimen Pada Ulasan Aplikasi Mobile Banking Menggunakan Metode Support Vector Machine dan Lexicon Based Features,†2019. [Daring]. Tersedia pada: http://j-ptiik.ub.ac.id

Y. Cahyono, “Analisis Sentiment Tweets Berbahasa Sunda Menggunakan Naive Bayes Classifier dengan Seleksi Feature Chi Squared Statistic,†vol. 4, no. 3, 2019, [Daring]. Tersedia pada: http://openjournal.unpam.ac.id/index.php/informatika

R. Apriani dkk., “ANALISIS SENTIMEN DENGAN NAÃVE BAYES TERHADAP KOMENTAR APLIKASI TOKOPEDIA,†2019.

A. Bayhaqy, S. Sfenrianto, K. Nainggolan, dan E. R. Kaburuan, “Sentiment Analysis about E-Commerce from Tweets Using Decision Tree, K-Nearest Neighbor, and Naïve Bayes,†dalam 2018 International Conference on Orange Technologies, ICOT 2018, Institute of Electrical and Electronics Engineers Inc., Jul 2018. doi: 10.1109/ICOT.2018.8705796.

Downloads

Published

2023-07-23

Issue

Vol. 7 No. 3 (2023): Juli 2023

Section

Articles

License

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

Authors who publish with this journal agree to the following terms:

  1. 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.
  2. 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.
  3. 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).