Analisis Sentimen Nasabah Terhadap Pengguna M-Banking Raya Indonesia Menggunakan Metode Naïve Bayes Berbasis NLP
TL;DR
Customer sentiment toward the use of the Raya Indonesia M-Banking app is analyzed using a Naïve Bayes method grounded in Natural Language Processing (NLP), and it is revealed that the main user complaints relate to login failures, transaction issues, and slow service responses.
Abstract
This study aims to analyze customer sentiment toward the use of the Raya Indonesia M-Banking app based on reviews on the Google Play Store using a Naïve Bayes method grounded in Natural Language Processing (NLP). Data was collected via web scraping, yielding 501 reviews, of which 474 were deemed valid after the selection process. The analysis stages included text preprocessing (case folding, cleansing, tokenizing, stopword removal, and stemming), feature extraction using TF-IDF, and classification using Multinomial Naïve Bayes with a training and testing data split of 80:20. The results of the study show that positive sentiment dominates at 62.66%, followed by negative sentiment at 31.43%, and neutral sentiment at 5.91%. Model evaluation yielded an accuracy of 75.79%, precision of 73.17%, recall of 75.79%, and an F1-score of 70.97%, indicating that the model performed quite well. Further analysis revealed that the main user complaints relate to login failures, transaction issues, and slow service responses; Thus, these findings provide a basis for evaluating and improving digital banking service quality.