Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen)
Yehezkiel Gunawan
Bina Nusantara University, Jakarta, Indonesia
Computer Science & IT Control & Systems Engineering

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

Found 1 Documents
Search

 1 
Unveiling Risks through Machine Learning: Analyzing Indonesian User Feedback Dataset of Capsule Hotel Experiences Yehezkiel Gunawan; Ford Lumban Gaol; Tokuro Matsuo
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 2 (2024): Edisi April
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i2.349

Abstract

The rise in popularity of capsule hotels as a unique and affordable lodging alternative, especially in Indonesia, has highlighted the necessity of skillfully recognizing and controlling any potential risks connected with such unusual lodgings. This paper introduces the large collection of 700 data examples that includes priority scores, problem areas, and verbatim user comments. Furthermore, we conduct a two-phase experiment using the Random Forest algorithm to classify risks. In the first stage, a custom BERT model for word embedding is integrated, and in the second stage, the pre-trained Indo LEM (BERT) model is used. Our results clearly demonstrate the higher effectiveness of the second step, demonstrating how the addition of Indo LEM as word embedding considerably improves classification accuracy. This demonstrates the enormous potential of utilizing cutting-edge machine learning techniques to improve risk classification processes, providing players in the capsule hotel industry with priceless information to improve safety regulations and better the overall guest experience. At (https://github.com/yehezkielgunawan/thesis-risk-classification), we provide full access to all relevant coding scripts for reference and replication as an addition to the dataset
Co-Authors Ford Lumban Gaol Tokuro Matsuo