Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal KLIK: Kajian Ilmiah Informatika dan Komputer
Cahyo Prakoso
Universitas Teknologi Yogyakarta, Yogyakarta
Computer Science & IT

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

Found 1 Documents
Search

 1 
Perbandingan Model Machine Learning dalam Analisis Sentimen Ulasan Pengunjung Keraton Yogyakarta pada Google Maps Cahyo Prakoso; Arief Hermawan
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 3 (2023): Desember 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i3.1419

Abstract

The Yogyakarta Palace, as a center of Javanese culture rich in history, art and tradition, attracts world attention and is the subject of various tourist reviews. In the digital era, these reviews are important for managing and improving tourism services. In particular, information technologies such as Google Maps facilitate public participation by providing a platform for visitors to share their experiences through reviews. These reviews provide important feedback for managers and potential visitors, while driving service improvements and innovation. Therefore, this research conducts review sentiment analysis using a Machine Learning model which is used to understand visitors' positive and negative views and compares three popular models in sentiment analysis, namely Naive Bayes, Logistic Regression, and Support Vector Machine (SVM). Review data collection uses the web scraping method with Selenium, followed by a preprocessing stage which includes translation, cleaning, normalization, tokenizing, removing stopwords, and stemming to prepare the data for sentiment analysis. Labeling is done based on review ratings, with a threshold below 4 for negative sentiment and 4 or 5 for positive. Based on data processing and analysis, the Support Vector Machine (SVM) model was proven to be the best model with an accuracy of 87.12% and an F1-Score of 90.91%, followed by Logistic Regression and Naive Bayes
Co-Authors Arief Hermawan