Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Sistemasi: Jurnal Sistem Informasi
Suadaa, Lya Hulliyatus
Unknown Affiliation
Computer Science & IT Electrical & Electronics Engineering

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

Found 1 Documents
Search
Journal : Sistemasi: Jurnal Sistem Informasi

 1 
Aspect-Based Sentiment Analysis using Adaptive Aspect on Tourist Reviews in Jakarta Setyawan, Ade Rifqy; Suadaa, Lya Hulliyatus; Yuniarto, Budi
Sistemasi: Jurnal Sistem Informasi Vol 13, No 6 (2024): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v13i6.4585

Abstract

Tourism is one of the business fields affected by the Covid-19 pandemic. The decline in the number of tourists, both domestic and foreign, has resulted in the contribution of the tourism business sector to Indonesia's GDP decreasing. The government is now preparing plans to restore and improve tourism in tourist destination areas, one of which is DKI Jakarta in order to increase visits by domestic and foreign tourists. In achieving these goals, this study propose to utilize reviews about tourist attractions in DKI Jakarta from Google Maps and extract public opinion by conducting aspect-based sentiment analysis. Multi-label classification is a common method that is often used in aspect-based sentiment analysis. However, the multi-label approach has limited flexibility in the aspects used. One alternative method that can be used is an adaptive aspect classification method which is more flexible if there are additional new aspects used. This research aims to automate sentiment classification of tourist reviews for each aspect by developing an aspect level sentiment analysis model with an adaptive aspect classification method which will be compared with multi-label classification as a baseline method. The models used in both methods are transfer learning IndoBERT. The adaptive aspect classification method with aspect level sentiment analysis has better performance in comparison to baseline method multi-label classification with accuracy values and F1-score respectively 0.90394 and 0.71504.
Co-Authors Setyawan, Ade Rifqy Yuniarto, Budi