EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Perbandingan Algoritma NBC Dan SVM Untuk Melakukan Analisis Sentimen Terhadap PP NO.82 Tahun 2021

Arum Mustika Rani, Nirwana Hendrastuty

Building of Informatics, Technology and Science (BITS) · 27.02.2025 · 6 (4) · 2139-2151

DOI: 10.47065/bits.v6i4.6496 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Building of Informatics, Technology and Science (BITS), online erschienen am 27.02.2025. Verfasst von Arum Mustika Rani und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Government Regulation (PP) No. 82/2021, which regulates the payment of pensions and allowances for Constitutional and Supreme Court Justices, has sparked public debate, especially after allegations of significant cuts to the Supreme Court's budget. This issue raises concerns regarding policy transparency, making it important to analyze public sentiment towards this PP. This study uses two sentiment analysis methods, namely Naïve Bayes Classifier (NBC) and Support Vector Machine (SVM), to evaluate public opinion based on data from Twitter. The dataset consists of 2,719 tweets that have gone through preprocessing stages, such as cleansing, stemming, and using SMOTE techniques, with 70% data division for training and 30% for model testing. This study tests the performance of NBC and SVM through four scenarios: (1) without stemming and without SMOTE, (2) without stemming with SMOTE, (3) with stemming without SMOTE, and (4) with stemming and SMOTE. The results show that SVM has a more stable performance than NBC in all scenarios. In the scenario without stemming and without SMOTE, both models recorded 100% accuracy, but NBC failed to detect positive sentiment accurately. When SMOTE was applied without stemming, NBC's accuracy decreased to 97%, while SVM still achieved a perfect accuracy of 100%. In the scenario with stemming without SMOTE, NBC recorded 97% accuracy, while SVM reached 99%. With the application of SMOTE and stemming, NBC accuracy decreased to 95%, while SVM again recorded a perfect accuracy of 100%. This study concludes that SVM is the best method for sentiment analysis of PP No. 82 of 2021, especially in scenarios with stemming and SMOTE, providing important insights into public opinion and confirming the superiority of SVM in sentiment classification related to public policy.

Zitieren

APA

Rani, A. M., & Hendrastuty, N. (2025). Perbandingan Algoritma NBC Dan SVM Untuk Melakukan Analisis Sentimen Terhadap PP NO.82 Tahun 2021. Building of Informatics, Technology and Science (BITS), 6(4), 2139-2151. https://doi.org/10.47065/bits.v6i4.6496

Vancouver

Rani AM, Hendrastuty N. Perbandingan Algoritma NBC Dan SVM Untuk Melakukan Analisis Sentimen Terhadap PP NO.82 Tahun 2021. Building of Informatics, Technology and Science (BITS). 2025;6(4):2139-2151. doi:10.47065/bits.v6i4.6496

BibTeX
@article{Rani2025,
  author = {Rani, Arum Mustika and Hendrastuty, Nirwana},
  title = {Perbandingan Algoritma NBC Dan SVM Untuk Melakukan Analisis Sentimen Terhadap PP NO.82 Tahun 2021},
  journal = {Building of Informatics, Technology and Science (BITS)},
  year = {2025},
  volume = {6},
  number = {4},
  pages = {2139--2151},
  doi = {10.47065/bits.v6i4.6496}
}
Kostenlos starten →