Sentiment Analysis and Service Aspects Prioritization of Indonesian Hotel Reviews Based on ABSA and Pareto Approach

DOI

10.2991/978-94-6239-717-0_11How to use a DOI?

Keywords

Aspect-Based Sentiment Analysis; BERT; Hotel Reviews; Pareto Diagram; Quality Tools

Abstract

In the hospitality industry, feedback reviews play a vital role in shaping perceptions and influencing decision-making. These reviews are not only valuable for stakeholders but also serve as important information resources, for instance, to improve customer satisfaction. However, the large volume of unstructured data poses challenges for the industry. This study addresses these challenges by implementing an aspect-based sentiment analysis (ABSA) approach to evaluate service quality, which is an advanced approach to sentiment analysis from Natural Language Processing (NLP). ABSA not only identifies the sentiment polarity of text but also important elements in feedback, including terms, categories, opinions, and sentiment polarity. Using IndoBERT, an Indonesian language pre-trained model of BERT, and feedback data from Indonesian hotels, the study classifies sentiments into “positive” and “negative” categories. Results from IndoBERT demonstrate impressive performance in this classification task, achieving an accuracy of 98.55% and an F1 score of 98.78%. This indicates its effectiveness in capturing the nuances of sentiment in Indonesian text. Additionally, the study employs a quality analysis approach utilizing a Pareto Diagram to prioritize issues. The Pareto 80/20 principle helps identify the 20% of aspects that contribute most significantly to 80% of customer dissatisfaction. The results suggest that management should pay attention to the aspects of services and beverages to improve customer satisfaction. By combining ABSA, IndoBERT, and the Pareto method, this study enhances sentiment analysis and supports informed decision-making based on data.

Copyright

© 2026 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  - Rais Sulaiman Rusid
AU  - Isti Surjandari
PY  - 2026
DA  - 2026/06/25
TI  - Sentiment Analysis and Service Aspects Prioritization of Indonesian Hotel Reviews Based on ABSA and Pareto Approach
BT  - Proceedings of the 19th International Conference on Quality in Research (QiR 2025)
PB  - Atlantis Press
SP  - 137
EP  - 153
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-717-0_11
DO  - 10.2991/978-94-6239-717-0_11
ID  - Rusid2026
ER  -