Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Jurnal Riset Informatika

SENTIMENT ANALYSIS OF USER REVIEWS BRI MOBILE APPLICATION WITH GRADIENT BOOST METHOD Nanang Ruhyana; Salsabila, Kanita; Agung, Andri; Mardiana, Tati
Jurnal Riset Informatika Vol. 7 No. 2 (2025): Maret 2025
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v7i2.342

Abstract

BRI Mobile application is a digital banking service launched in 2019 by Bank Rakyat Indonesia, which provides facilities such as mobile banking, internet banking, and electronic money. The presence of this application aims to facilitate customers in accessing and managing financial services efficiently through mobile devices. Reviews have become a very important source on platforms such as Google Playstore become a very important source of information to evaluate and improve service quality. However, manually identifying sentiment representations from thousands of reviews is a time-consuming and inefficient process. This research aims to perform sentiment analysis automatically on BRI Mobile application user reviews by utilizing text mining methods. The sentiment classification process is carried out using the Gradient Boosting algorithm approach and initial analysis using the VADER Sentiment method to provide initial data labelling. Based on the classification results, 344 data with positive sentiment, 333 data with negative sentiment, and 333 data with neutral sentiment were obtained. The model built was then evaluated using the accuracy metric, and an accuracy value of 97% was obtained. The results of this research are expected to be a strategic input for application developers in understanding user perceptions more objectively and efficiently.
Approaches to Customer Types Classification Method in the Supermarket Nanang Ruhyana; Mardiana, Tati
Jurnal Riset Informatika Vol. 6 No. 1 (2023): December 2023
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1128.804 KB) | DOI: 10.34288/jri.v6i1.269

Abstract

The development of the retail industry in the economy is very rapid so it provides good economic growth, one of the retailers is supermarkets, in supermarkets consumers can buy goods directly, so consumers must be served well. The problem is how supermarkets can continue to increase their sales results, because there is a lot of competition from supermarket competitors, so the marketing team when creating events or promotions must be right on target so that loyalty for member or non-member customers can be measured, which will be used as the right marketing strategy and can increase customer satisfaction when the customer is satisfied with the services, products and promotional activities at the supermarket, the customer will continue to make purchases and will increase the results of achieving good sales. Based on this problem, how will this research apply the classification method, so that when we can make predictions from supermarket sales data for member and non-member customers, there will be a lot of insight for the marketing team, so that marketing activities are right on target for member or non-member customers. This research uses machine learning methods for data classification, using the Support Vector Machine (SVM) and Naïve Bayes algorithms. The results of this research are from the Support Vector Machine (SVM) algorithm. Accuracy is 0.493 while using the Naïve Bayes algorithm is 0.535. From the results of this research, the use of the Naïve Bayes algorithm is better than SVM so that it can approach the prediction of member and non-member customer classification in supermarket data in this research.
Integration of Adasyn Method with Decision Tree Algorithm in Handling Imbalance Class for Loan Status Prediction Ami Rahmawati; Yulianti, Ita; Mardiana, Tati; Pribadi, Denny
Jurnal Riset Informatika Vol. 6 No. 3 (2024): June 2024
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (761.285 KB) | DOI: 10.34288/jri.v6i3.299

Abstract

Determining the provision of credit is generally carried out based on measuring credibility using credit analysis principles (5C principles). However, this method requires quite a long processing time and is very susceptible to subjective judgments which might influence the final results. This research uses data mining techniques by developing modeling on loan status prediction datasets. The stages in this research include data preprocessing, modeling, and evaluation using accuracy metrics and ROC graphs. In this analysis, it is known that there is a class imbalance in the processed dataset, so an oversampling technique must be carried out. This research uses the ADASYN (Adaptive Synthetic) Oversampling technique to ensure the class distribution is more balanced. Then, the ADASYN technique is integrated with the Decision Tree Algorithm to build a prediction model. The research results show that the two methods can increase prediction accuracy by 12.22%, from 73,91% to 85.22%. This improvement was obtained by comparing the accuracy results before and after using the ADASYN Oversampling technique. This finding is important because it proves that implementing such integration modeling can significantly improve the performance of classification models and provide strong potential for practical application in helping more effective loan status predictions.