Article Per Year (5 Year)
p-Index From 2021 - 2026
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Katherine Ivana Ruslim
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 Mobile Banking Menggunakan Metode Support Vector Machine dan Lexicon Based Features Katherine Ivana Ruslim; Putra Pandu Adikara; Indriati Indriati
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 7 (2019): Juli 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1165.474 KB)

Abstract

Sentiment analysis is a very popular field of research in text mining. The basic idea of ​​sentiment analysis is finding the polarity of the document and classifying it into positive or negative. The text documents used in the research are reviews on the Google Play Store regarding the mobile banking application. Support Vector Machine is a method used and added Lexicon Based Features as additional feature besides using the Bag of Words. The research data is 500 data by dividing 90% training data and 10% test data. The system evaluation results obtained with a combination of Bag of Words and Lexicon Based Features are higher than the results of system evaluations that only use the Bag of Words and systems that only use Lexicon Based Features. The evaluation results obtained by the combination of the two features with testing using 10 fold cross validation are accuracy = 0,846, recall = 0,846, precision = 0,864, and f-measure = 0,855 with the Support Vector Machine parameter value used is the best parameter value of sigma kernel RBF = 3, lambda = 0,1, gamma = 0,001, complexity = 0,1, epsilon = 0,001, and iteration = 50.
Co-Authors Indriati Indriati Putra Pandu Adikara