Analisis Kepuasan Pengguna Aplikasi Gopay Menggunakan Algoritma Naïve Bayes Dan K-Fold Cross Validation
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AEEEY7T86" target="_blank" >RIV/00216208:11320/26:EEEY7T86 - isvavai.cz</a>
Výsledek na webu
<a href="https://repository.bsi.ac.id/repo/71147/ANALISIS-KEPUASAN-PENGGUNA-APLIKASI-GOPAY-MENGGUNAKAN-ALGORITMA-NAÏVE-BAYES-DAN-K-FOLD-CROSS-VALIDATION" target="_blank" >https://repository.bsi.ac.id/repo/71147/ANALISIS-KEPUASAN-PENGGUNA-APLIKASI-GOPAY-MENGGUNAKAN-ALGORITMA-NAÏVE-BAYES-DAN-K-FOLD-CROSS-VALIDATION</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Analisis Kepuasan Pengguna Aplikasi Gopay Menggunakan Algoritma Naïve Bayes Dan K-Fold Cross Validation
Popis výsledku v původním jazyce
The rapid advancement of digital technology has significantly increased the adoption of digital wallet services in Indonesia, one of which is the GoPay application. This study aims to analyze user satisfaction with GoPay based on user reviews from the Google Play Store. The classification method used is the Naïve Bayes algorithm, with model validation performed using the K-Fold Cross Validation technique. A total of 3,000 reviews were collected through web scraping and then preprocessed using several text preprocessing steps including cleansing, case folding, tokenizing, stopword removal, and stemming. The data was automatically labeled using the IndoBERT model and classified into two satisfaction categories. The classification results show that the Naïve Bayes algorithm achieved an accuracy of 93,22%, with a precision of 92,60%, recall of 95,58%, and an f1-score of 94.11%. Validation using 10-fold cross-validation resulted in an average accuracy of 92.38%. These results indicate that the model demonstrates strong classification performance and stable generalization on unseen data. This research is expected to contribute to improving GoPay's service quality and serve as a reference for the implementation of machine learning techniques in user satisfaction analysis.
Název v anglickém jazyce
Analisis Kepuasan Pengguna Aplikasi Gopay Menggunakan Algoritma Naïve Bayes Dan K-Fold Cross Validation
Popis výsledku anglicky
The rapid advancement of digital technology has significantly increased the adoption of digital wallet services in Indonesia, one of which is the GoPay application. This study aims to analyze user satisfaction with GoPay based on user reviews from the Google Play Store. The classification method used is the Naïve Bayes algorithm, with model validation performed using the K-Fold Cross Validation technique. A total of 3,000 reviews were collected through web scraping and then preprocessed using several text preprocessing steps including cleansing, case folding, tokenizing, stopword removal, and stemming. The data was automatically labeled using the IndoBERT model and classified into two satisfaction categories. The classification results show that the Naïve Bayes algorithm achieved an accuracy of 93,22%, with a precision of 92,60%, recall of 95,58%, and an f1-score of 94.11%. Validation using 10-fold cross-validation resulted in an average accuracy of 92.38%. These results indicate that the model demonstrates strong classification performance and stable generalization on unseen data. This research is expected to contribute to improving GoPay's service quality and serve as a reference for the implementation of machine learning techniques in user satisfaction analysis.
Klasifikace
Druh
J<sub>ost</sub> - Ostatní články v recenzovaných periodicích
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2025
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
Jurnal Ilmiah Informatika
ISSN
2615-1049
e-ISSN
—
Svazek periodika
2025
Číslo periodika v rámci svazku
2025
Stát vydavatele periodika
US - Spojené státy americké
Počet stran výsledku
60
Strana od-do
1-60
Kód UT WoS článku
—
EID výsledku v databázi Scopus
—