Topic modeling on Natural Tourism Objects in West Bandung Regency Based on Reviews from Google Maps with the Latent Semantic Analysis (LSA) Method

DOI

10.2991/978-94-6463-366-5_7How to use a DOI?

Keywords

data mining; latent semantic analysis; natural attractions; topic modeling; tourist reviews

Abstract

The COVID-19 pandemic has prompted a transformation in Indonesia’s tourism sector to accommodate changes in traveler preferences during the pandemic and to stabilize the tourism industry post-pandemic. West Bandung Regency, renowned for its abundant natural attractions, holds significant potential for developing tourist destinations. In support of this, the Tourism and Culture Office of West Java Province has devised a customer-centric “new normal strategy.” This research employs topic modeling using latent semantic analysis (LSA) on traveler reviews from Google Maps. The study examined various scenarios and found that the optimal number of topics is 2, utilizing advanced stopword pre-processing and a bag of words (BoW) representation, resulting in a coherence score metric of 0.717. The choice of two topics is based on the highest coherence score metric. Opting for more topics would lead to redundancy, with additional topics merely reiterating discussions covered in the previous ones. The analysis of traveler reviews revealed keywords that frequently appear, such as accessibility, location, parking, tickets, beauty, nature, and facilities. The analysis of these keywords suggests that tourists frequently discuss topics concerning accessibility to attractions, facilities available, and the overall atmosphere experienced at these tourist spots. Based on these findings, recommendations are proposed, including enhancing accessibility, improving parking and payment systems, upgrading photo spots, and enhancing facilities at waterfalls and natural attractions in West Bandung Regency. By implementing the outcomes of this research, the government can take appropriate actions to improve the traveler experience, optimize natural tourist attractions, and promote West Bandung Regency as an attractive tourism destination post-pandemic.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - I G. N. A. Agni Prema N
AU  - Faqih Hamami
AU  - Ekky Novriza Alam
PY  - 2024
DA  - 2024/02/02
TI  - Topic modeling on Natural Tourism Objects in West Bandung Regency Based on Reviews from Google Maps with the Latent Semantic Analysis (LSA) Method
BT  - Proceedings of the 2023 1st International Conference on Advanced Informatics and Intelligent Information Systems (ICAI3S 2023)
PB  - Atlantis Press
SP  - 61
EP  - 70
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-366-5_7
DO  - 10.2991/978-94-6463-366-5_7
ID  - PremaN2024
ER  -