Aspect-Based Sentiment Analysis on Indonesian Presidential Election Using Deep Learning

Authors

  • Fadillah Said Universitas Nusa Mandiri
  • Lindung Parningotan Manik Universitas Nusa Mandiri

DOI:

https://doi.org/10.31294/paradigma.v24i2.1415

Keywords:

sentiment analyst, deep learning, classification

Abstract

The 2019 presidential election is a presidential election that has been a hot topic of discussion for some time, and people have even talked about this topic since 2018 on the internet. In predicting the winner of the presidential election, previous research has conducted research on the aspect-based sentiment analysis (ABSA) dataset of the 2019 presidential election using machine learning algorithms such as the Support Vector Machine (SVM), Naive Bayes (NB), and K-Nearest Neighbors (KNN) and produces good accuracy. This study proposes a deep learning method using the BERT (Bidirectional Encoder Representation Form Transformers) and RoBERTa (A Robustly Optimized BERT Pretraining Approach) models. The results of this study indicate that the indobenchmark BERT and RoBERTa base-Indonesian single label classification models on target features with preprocessing produce the best accuracy of 98.02%. The indolem BERT model and the indobenchmark single label classification on the target feature without preprocessing produce the best accuracy of 98.02%. The BERT indobenchmark single label classification model on aspect features with preprocessing produces the best accuracy of 74.26%. The BERT indolem single label classification model on aspect features without preprocessing produces the best accuracy of 74.26%. The BERT indolem single label classification model on the sentiment feature with preprocessing produces the best accuracy of 93.07%. The BERT indolem single label classification model on the sentiment feature without preprocessing produces the best accuracy of 94.06%. The BERT indobenchmark multi label classification model with preprocessing produces the best accuracy of 98.66%. The BERT indobenchmark multi label classification model without preprocessing produces the best accuracy of 98.66%.

References

Budiharto, W., & Meiliana, M. (2018). Prediction and analysis of Indonesia Presidential election from Twitter using sentiment analysis. Journal of Big Data, 5(1), 1–10. https://doi.org/10.1186/s40537-018-0164-1

Hamid Mughal, M. J. (2018). Data mining: Web data mining techniques, tools and algorithms: An overview. International Journal of Advanced Computer Science and Applications, 9(6), 208–215. https://doi.org/10.14569/IJACSA.2018.090630

Hoang, M., Bihorac, O. A., & Rouces, J. (2019). Aspect-Based Sentiment Analysis using BERT. Proceedings of the 22nd Nordic Conference on Computational Linguistics, 187–196. https://www.aclweb.org/anthology/W19-6120

Manik, L. P., Febri Mustika, H., Akbar, Z., Kartika, Y. A., Ridwan Saleh, D., Setiawan, F. A., & Atman Satya, I. (2020). Aspect-Based Sentiment Analysis on Candidate Character Traits in Indonesian Presidential Election. Proceeding - 2020 International Conference on Radar, Antenna, Microwave, Electronics and Telecommunications, ICRAMET 2020, 224–228. https://doi.org/10.1109/ICRAMET51080.2020.9298595

Manjarres, A. V., Sandoval, L. G. M., & Suárez, M. J. S. (2018). Data mining techniques applied in educational environments: Literature review. Digital Education Review, 33, 235–266. https://doi.org/10.1344/der.2018.33.235-266

Otter, D. W., Medina, J. R., & Kalita, J. K. (2021). A Survey of the Usages of Deep Learning for Natural Language Processing. IEEE Transactions on Neural Networks and Learning Systems, 32(2), 604–624. https://doi.org/10.1109/TNNLS.2020.2979670

Suciati, A., Wibisono, A., & Mursanto, P. (2019). Twitter Buzzer Detection for Indonesian Presidential Election. ICICOS 2019 - 3rd International Conference on Informatics and Computational Sciences: Accelerating Informatics and Computational Research for Smarter Society in The Era of Industry 4.0, Proceedings. https://doi.org/10.1109/ICICoS48119.2019.8982529

Sun, C., Huang, L., & Qiu, X. (2019). Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence. NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, 1, 380–385.

Waasiu, A., B, A. I., & Lawi, A. (2021). Klasifikasi Audio Cats and Dogs Menggunakan Model Artifical Neural Network Multi-perceptron. 56–61.

Xin, Y., Kong, L., Liu, Z., Chen, Y., Li, Y., Zhu, H., Gao, M., Hou, H., & Wang, C. (2018). Machine Learning and Deep Learning Methods for Cybersecurity. IEEE Access, 6(c), 35365–35381. https://doi.org/10.1109/ACCESS.2018.2836950

Downloads

Published

2022-09-20

How to Cite

Said, F., & Manik, L. P. (2022). Aspect-Based Sentiment Analysis on Indonesian Presidential Election Using Deep Learning. Paradigma - Jurnal Komputer Dan Informatika, 24(2), 160-167. https://doi.org/10.31294/paradigma.v24i2.1415