ANALISIS SENTIMEN PENGGUNA APLIKASI JAMSOSTEK MOBILE (JMO) PADA APPSTORE MENGGUNAKAN METODE NAIVE BAYES

Karin Kusuma Dewi; Ismi Kaniawulan; Candra Dewi Lestari

doi:10.51876/simtek.v8i2.286

Authors

Karin Kusuma Dewi Sekolah Tinggi Teknologi Wastukancana
Ismi Kaniawulan Sekolah Tinggi Teknologi Wastukancana
Candra Dewi Lestari Sekolah Tinggi Teknologi Wastukancana

DOI:

https://doi.org/10.51876/simtek.v8i2.286

Keywords:

Analisis Sentimen,, Naive Bayes, App Store, Jamsostek Mobile, Google Collaboratory

Abstract

The use of Jamsostek Mobile has problems that often occur, namely failure to update data on the JMO application, digital cards that do not appear on the JMO application, data update failures and access failures. To overcome this, BPJS participants are faced with BPJS branches or companies. This is an obstacle that should be overcome through optimizing regulations from the BPJS so that there are no complaints from the public regarding this matter.

Jamsostek Mobile is an application implemented by BPJS Ketenagakerjaan to make it easier for users to carry out JHT simulations, check JHT balances, check details for JHT contributions and pension benefits, and make JHT claims. This application can be accessed on the App Store and Playstore. The implementation of the application turned out to generate several comments or reviews from users both in the App Store and Play Store.

This study aims to analyze sentiment from user reviews on the App Store with the stages of Scraping, Labeling, Cleaning, Preprocessing Text, Class Naive Bayes, TF-IDF, Evaluation, Visualization using Google Collaboratory tools

From the results of research on the sentiment analysis of users of the Jamsostek Mobile application on the AppStore platform, which totaled 2001 data and had passed the preprocessing text stage consisting of filtering, tokenization, transformation and classification using the Naïve Bayes algorithm and evaluation of data with a confusion matrix using Google Collaboratory, it can be interpreted that the results from reviews of the use of negative JMO applications with a proportion of 96% in accuracy (accuracy), 96% in value precision, and a success rate (recall) of 100%. This value indicates that the naïve Bayes classification algorithm is considered quite good in processing review data, because the proportion of accuracy is 96%. Based on this value, it proves that the sentiment or reviews of JMO application users on the App Store platform are negative.

Keywords: Sentimen Analysis, Naive Bayes, App Store, Jamsostek Mobile, Google Collaboratory