Evaluating Machine Learning Approaches for Sentiment Analysis of Internet Service Providers in Indonesia: Naïve Bayes vs. Gradient Boosting

DOI

10.2991/978-94-6463-878-3_58How to use a DOI?

Keywords

Gradient Boosting; Naïve Bayes Sentiment Analysis; Machine Learning

Abstract

Customer satisfaction has become a crucial metric for the business sustainability of Internet Service Providers (ISPs) amidst fierce industrial competition in Indonesia. Automated sentiment analysis on social media offers a solution to efficiently monitor public opinion. This study aims to comprehensively evaluate and compare two machine learning algorithms, Naïve Bayes (NB) and Gradient Boosting (GB), for the task of sentiment classification on Indonesian ISP user reviews collected from the Twitter platform. The research methodology encompasses several optimization stages, including hyperparameter tuning and the handling of imbalanced data using the Synthetic Minority Over-sampling Technique (SMOTE), to ensure a fair and in-depth comparison. The experimental results indicate that Gradient Boosting consistently outperforms Naïve Bayes. The best-performing model, Gradient Boosting optimized with tuning and SMOTE, achieved an overall accuracy of 85%. More importantly, this model demonstrated a superior capability in identifying negative sentiment, achieving a recall score of 93%, which is a valuable capability for practical applications such as customer complaint detection. This study concludes that the optimized Gradient Boosting approach constitutes a more robust and reliable solution for sentiment analysis in this domain.

Copyright

© 2025 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 Gusti Ngurah Bagus Catur Bawa
AU  - Made Pradnyana Ambara
AU  - I Wayan Suasnawa
AU  - Anak Agung Ngurah Gde Sapteka
AU  - I Komang Wiratama
AU  - Ida Bagus Putra Manuaba
PY  - 2025
DA  - 2025/10/31
TI  - Evaluating Machine Learning Approaches for Sentiment Analysis of Internet Service Providers in Indonesia: Naïve Bayes vs. Gradient Boosting
BT  - Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2025 (ICOSTAS-EAS 2025)
PB  - Atlantis Press
SP  - 524
EP  - 532
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-878-3_58
DO  - 10.2991/978-94-6463-878-3_58
ID  - Bawa2025
ER  -