Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Indriya Dewi Onantya
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 Pada Ulasan Aplikasi BCA Mobile Menggunakan BM25 Dan Improved K-Nearest Neighbor Indriya Dewi Onantya; Indriati Indriati; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (768.962 KB)

Abstract

Mobile banking application is one of the applications that can provide convenience in human activities. One of these applications is BCA Mobile. This application makes users easily to do financial activities without having to go to the relevant bank. This is an option that is very useful for users who have a busy life in their daily lives. From existing mobile applications, there are no features that can be used to group or filter positive and negative reviews. To find out reviews that are classified as positive or negative reviews, a sentiment analysis review is needed. The analysis process begins with pre-processing data, weighing words using the BM25 algorithm, and the process of classification using Improved K-Nearest Neighbor. The results obtained based on the result of 5-fold cross-validation and get the best k-value at 10, with the result of precision value are 0.946, recall value is 0.934, f-measure value is 0.939, and an accuracy is 0.942. These results get fluctuating measurement results because of the amount of k-value. However, it does not influence by the amount classes of data, because even though there are different amounts or proportions of data classes, the new k-value adjust to the amount of data based on the value of each class.
Co-Authors Indriati Indriati Putra Pandu Adikara