Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Fanka Angelina Larasati
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Analisis Sentimen Ulasan Aplikasi Dana dengan Metode Random Forest Fanka Angelina Larasati; Dian Eka Ratnawati; Buce Trias Hanggara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 9 (2022): September 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Digital Wallet is an electronic application that can be used to make financial transactions online, without physical money and without cards, users only use smartphones in conducting financial transactions. A popular digital wallet application during this pandemic is Dana. The Dana app has many users, so there are often positive, negative and neutral reviews that are irrelevant to the rating given on the Google Play Store. The Dana application review data will be obtained using the Web Scraping technique using the Google-Play-Scraper API. The data from the scraping will then be done by text preprocessing to clean the text so that the data can be executed. Sentiment analysis can detect whether a text contains positive, negative or neutral opinions from user reviews that do not match the rating. Random Forest is a method in analysis that consists of several decision trees as a classifier. In this study, the random forest method was used by dividing three classes of sentiment, namely positive, negative and neutral. Also taking evaluation indicators, namely accuracy, recall, precision and f-measure. The test is carried out based on the number of trees and the depth of the tree to 1354 data by dividing the data by 250 data per class. Based on the results of tests and analyzes that have been carried out, with a comparison of training data and test data of 80%: 20%, namely precision 84%, recall 84%, F1-Score 84% and accuracy of 84% with a tree depth of 65 and a tree number of 400.
Co-Authors Buce Trias Hanggara Dian Eka Ratnawati