Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Jurnal Riset Informatika

COMPARISON OF CLASSIFICATION ALGORITHMS FOR ANALYSIS SENTIMENT OF FORMULA E IMPLEMENTATION IN INDONESIA Fachri Amsury; Nanang Ruhyana; Tati Mardiana
Jurnal Riset Informatika Vol 4 No 3 (2022): Period of June 2022
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (934.443 KB) | DOI: 10.34288/jri.v4i3.400

Abstract

The Formula E racing series has become one of the world's most prestigious competitions. In 2022, Indonesia hosted the famous Formula E race. The event possesses the potential for economic benefits for Indonesia worth 78 million euros through the arrival of 35,000 spectators. Indonesians are enthusiastic about Formula E since it allows their nation to encourage tourists and gain international prominence. However, some people do not support this event. Since they regard that amid the COVID-19 pandemic, it is preferable for the government to focus on people affected by the pandemic rather than support a Formula E event. This study compares the Support Vector Machine and Naive Bayes algorithms in classifying public opinion in the Formula E race. This study gets its information from user comments on social media platforms, especially Twitter. The stages start with text preprocessing and include cleaning, case folding, tokenization, filtering, and stemming. Proceed with weighting using the TF-IDF approach. Data testing uses a confusion matrix to evaluate the classification results by testing accuracy, precision, and recall. Categorizing public opinion using the SVM algorithm has an accuracy of 82 percent, a precision of 97.86 percent, and a recall of 77.90 percent. On the other hand, the accuracy of the Naive Bayes technique is more limited, at 87.54 percent. Society's opinion on Twitter shows positive sentiment towards implementing Formula E.
Implementation of the Saw Method to Discover the Optimum Internet Service Recommendations for Online Gaming Gunawan Gunawan; Ita Yulianti; Ami Rahmawati; Tati Mardiana; Nanang Ruhyana
Jurnal Riset Informatika Vol 5 No 3 (2023): Priode of June 2023
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v5i3.547

Abstract

Currently, the development and use of the Internet have a more complex function so that it can change the paradigm of people's lives, including in aspects of entertainment, especially games. With the rise of numerous ISPs in Indonesia, different internet service packages are now available, particularly for gamers, such as Indihome, Biznet, First Media, and My Republic. The variety of services makes it difficult for users to choose an internet package that suits their needs. Therefore, this research aims to build a decision support system that can facilitate users in choosing the ideal internet service for gamers based on five criteria: quota, network speed, connection, cost, and the number of users using the SAW method. The data collection methods used are observation, questionnaires, and interviews. The research results obtained from data processing using the SAW method through Microsoft Excel are then implemented into a website-based program. With this program, it is hoped that it can be a tool for users in determining the service package to be purchased.
Implementation of the Saw Method to Discover the Optimum Internet Service Recommendations for Online Gaming Gunawan Gunawan; Ita Yulianti; Ami Rahmawati; Tati Mardiana; Nanang Ruhyana
Jurnal Riset Informatika Vol. 5 No. 3 (2023): June 2023
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (759.546 KB) | DOI: 10.34288/jri.v5i3.232

Abstract

Currently, the development and use of the Internet have a more complex function so that it can change the paradigm of people's lives, including in aspects of entertainment, especially games. With the rise of numerous ISPs in Indonesia, different internet service packages are now available, particularly for gamers, such as Indihome, Biznet, First Media, and My Republic. The variety of services makes it difficult for users to choose an internet package that suits their needs. Therefore, this research aims to build a decision support system that can facilitate users in choosing the ideal internet service for gamers based on five criteria: quota, network speed, connection, cost, and the number of users using the SAW method. The data collection methods used are observation, questionnaires, and interviews. The research results obtained from data processing using the SAW method through Microsoft Excel are then implemented into a website-based program. With this program, it is hoped that it can be a tool for users in determining the service package to be purchased.
SENTIMENT ANALYSIS OF USER REVIEWS BRI MOBILE APPLICATION WITH GRADIENT BOOST METHOD Nanang Ruhyana; Kanita Salsabila; Andri Agung; Tati Mardiana
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 sourceĀ 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.