Detecting Early Signs of Overtourism in Bali: Sentiment and Multiclass Analysis Using BERT and LSTM

The rapid growth of tourism in Bali has made it one of the destinations facing overtourism, according to the World Travel & Tourism Council (WTTC). This study analyzes tourist perceptions of overtourism in Bali using TripAdvisor reviews from 2018 to 2024. By applying BERT and LSTM models, the study identifies tourist perceptions through sentiment analysis of destinations and multiclass issue classification. The results show that LSTM achieved slightly higher accuracy than BERT, with 77% for sentiment analysis and 92% for overtourism issue classification. Destination sentiment analysis showed an average of 70% positive sentiment, with some destinations recording below-average positive sentiment, reflecting less satisfactory tourist experiences in those areas. The Physical Environment issue was the most frequently discussed topic by tourists, while the highest negative sentiment was linked to the Tourist Numbers issue, indicating discomfort with overcrowding. The strong correlation between Tourist Numbers and Physical Environment shows that environmental pressure increases as visitor numbers grow. These findings highlight the importance of sustainable tourism management to address overtourism challenges and ensure the long-term sustainability of Bali's tourism sector.

Authors

Institutions

Publication Details

Published
2025-02-03
DOI
https://doi.org/10.1109/icadeis65852.2025.10933341
Citations
1
Primary Topic
Data Mining and Machine Learning Applications
Type
article
Field-Weighted Citation Impact
3.25
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Detecting Early Signs of Overtourism in Bali: Sentiment and Multiclass Analysis Using BERT and LSTM

Herry Irawan, Dini Khairina
1 citations
Data Mining and Machine Learning Applications
3.25
article

Detecting Early Signs of Overtourism in Bali: Sentiment and Multiclass Analysis Using BERT and LSTM

Herry Irawan, Dini Khairina
article en
1 citations

Abstract

The rapid growth of tourism in Bali has made it one of the destinations facing overtourism, according to the World Travel & Tourism Council (WTTC). This study analyzes tourist perceptions of overtourism in Bali using TripAdvisor reviews from 2018 to 2024. By applying BERT and LSTM models, the study identifies tourist perceptions through sentiment analysis of destinations and multiclass issue classification. The results show that LSTM achieved slightly higher accuracy than BERT, with 77% for sentiment analysis and 92% for overtourism issue classification. Destination sentiment analysis showed an average of 70% positive sentiment, with some destinations recording below-average positive sentiment, reflecting less satisfactory tourist experiences in those areas. The Physical Environment issue was the most frequently discussed topic by tourists, while the highest negative sentiment was linked to the Tourist Numbers issue, indicating discomfort with overcrowding. The strong correlation between Tourist Numbers and Physical Environment shows that environmental pressure increases as visitor numbers grow. These findings highlight the importance of sustainable tourism management to address overtourism challenges and ensure the long-term sustainability of Bali's tourism sector.

Telkom University (ID)
Openalex Percentile: Top 10%
Data Mining and Machine Learning Applications
3.25
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Detecting Early Signs of Overtourism in Bali: Sentiment and Multiclass Analysis Using BERT and LSTM — Herry Irawan, Dini Khairina · (2025) | TGRS Research Map | TGRS