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
Ghani Fikri Baihaqi
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 Wisata Alun-Alun Kota Batu menggunakan Algoritma Support Vector Machine Ghani Fikri Baihaqi; Dian Eka Ratnawati; Buce Trias Hanggara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 12 (2022): Desember 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Batu town square is one of the tourist destinations in Batu city which is located in the center of Batu city and is an icon of the city. Batu City is also the number one tourist destination center in East Java with more than three million tourists every year. Batu City Square is a cheap tourist attraction which is the main destination for tourists visiting Batu City before heading to other tourist objects in this city. The tourism manager of Batu City Square, namely the Tourism Goverment, needs to know the perspective of visitors as evaluation material in building better infrastructure and services. Acquisition of visitor review data for the Batu City Square tour was obtained from the Tripadvisor website with data collection techniques using web scraping. Reviews from Tripadvisor will be categorized into two classes, positive and negative. Before classifying, text preprocessing is carried out to process the data into more structured data for research needs and to weight words using the Term Frequency - Inverse Document method. Classification is done using the Support Vector Machine algorithm. Classification uses data of 240 positive and negative data for classification in each Kernel. The best results in testing using the Support Vector Machine algorithm are testing on the rbf Kernel and a C value of 50. The Cross Validation used in this test is as many as 8 folds and produces an average value on the parameters and the number of folds, namely accuracy of 89.58%, precision of 90.73%, recall of 89.48%, f-measure of 89.45%, and specificity of 91.27%.
Co-Authors Buce Trias Hanggara Dian Eka Ratnawati