Enhancing the Accuracy of a Sentiment Analysis Model for Election Prediction Using a Hybrid Approach: An Experiment on Indonesian Tweets

DOI

10.2991/978-94-6463-926-1_85How to use a DOI?

Keywords

Election Predict; Hybrid Model; Sentiment Analysis

Abstract

Sentiment analysis on social media platforms presents unique challenges due to the informal, noisy, and often imbalanced nature of user-generated content. This study proposes a hybrid model that integrates a transformer-based deep learning approach, IndoBERTweet, with probabilistic reasoning using Naive Bayes to improve sentiment classification performance in the context of Indonesian political discourse. Experimental evaluations across multiple train–test split scenarios (70:30, 80:20, and 90:10) demonstrate that the proposed model consistently outperforms a traditional probabilistic baseline in terms of accuracy, precision, and recall. The highest performance was observed with an 80:20 split, achieving 0.82 accuracy, 0.83 precision, and 0.82 recall. These results indicate the effectiveness of combining contextual language embeddings with probabilistic classification. While this study utilizes a pretrained IndoBERTweet model without fine-tuning, future work will explore fine-tuning strategies and resampling techniques to further enhance performance. The findings suggest a promising direction for sentiment analysis in low-resource languages such as Indonesian.

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  - Rizqia Lestika Atimi
AU  - Ar-Razy Muhammad
AU  - Putri Nur Fadillah
AU  - SP Irianto
PY  - 2025
DA  - 2025/12/31
TI  - Enhancing the Accuracy of a Sentiment Analysis Model for Election Prediction Using a Hybrid Approach: An Experiment on Indonesian Tweets
BT  - Proceedings of the International Conference on Applied Science and Technology on Engineering Science 2025 (iCAST-ES 2025)
PB  - Atlantis Press
SP  - 759
EP  - 767
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-926-1_85
DO  - 10.2991/978-94-6463-926-1_85
ID  - Atimi2025
ER  -