SARININGTIAS, RATRI (2025) ANALISIS SENTIMEN MASYARAKAT TERHADAP KENAIKAN PPN MENJADI 12% TAHUN 2025 DI MEDIA SOSIAL X MENGGUNAKAN ALGORITMA SVM DAN NAIVE BAYES. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (374kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (37kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (111kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (112kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (927kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (29kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (170kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (824kB) |
Abstract
The policy of increasing the Value Added Tax (VAT) rate to 12% in 2025 has sparked various public reactions, particularly on the social media platform X (formerly Twitter). This study aims to classify public sentiment toward the policy using two text classification algorithms: Support Vector Machine (SVM) and Multinomial Naïve Bayes. To address class imbalance in the sentiment data (positive, negative, neutral), the Synthetic Minority Over-sampling Technique (SMOTE) was applied to the training data. Data were collected through crawling using keywords related to the VAT increase issue, followed by preprocessing stages, TF-IDF transformation, and data splitting into two scenarios (80:20 and 70:30). The performance of the models was evaluated using accuracy, precision, recall, F1-score, and Area Under the Curve (AUC) metrics. The results show that the SVM algorithm without SMOTE achieved the best performance with an accuracy of 90.52% and an AUC of 0.860. Meanwhile, the Naïve Bayes algorithm showed improved performance after SMOTE was applied, particularly in recall and F1-score, although overall performance remained lower than that of SVM. Therefore, SVM is considered more reliable for sentiment classification tasks, while SMOTE proved effective in enhancing the performance of Naïve Bayes, especially in handling imbalanced datasets. Kata kunci: Sentiment analysis, VAT 12%, social media X, Naïve Bayes, Support Vector Machine, SMOTE Kebijakan kenaikan tarif Pajak Pertambahan Nilai (PPN) menjadi 12% pada tahun 2025 memicu beragam reaksi di masyarakat, terutama di media sosial X (sebelumnya Twitter). Penelitian ini bertujuan untuk menganalisis sentimen publik terhadap kebijakan tersebut dengan menggunakan dua algoritma klasifikasi teks, yaitu Support Vector Machine (SVM) dan Naïve Bayes, serta menerapkan metode Synthetic Minority Over-sampling Technique (SMOTE) untuk mengatasi ketidakseimbangan data antar kelas sentimen. Data dikumpulkan melalui teknik crawling dari media sosial X menggunakan kata kunci terkait isu kenaikan PPN, kemudian diproses melalui tahapan preprocessing, transformasi TF-IDF, dan pembagian data dalam dua skenario (80:20 dan 70:30). Evaluasi kinerja model dilakukan menggunakan metrik akurasi, precision, recall, f1-score, dan Area Under Curve (AUC). Hasil penelitian menunjukkan bahwa algoritma SVM tanpa SMOTE memberikan performa terbaik dengan akurasi sebesar 90,52% dan AUC 0,860, sementara Naïve Bayes menunjukkan peningkatan kinerja setelah penerapan SMOTE, khususnya pada recall dan f1-score. Temuan ini menunjukkan bahwa algoritma SVM lebih andal dalam klasifikasi sentimen teks secara umum, sedangkan SMOTE efektif dalam meningkatkan performa algoritma Naïve Bayes pada data yang tidak seimbang. Kata kunci: Analisis sentimen, PPN 12%, media sosial X, Naïve Bayes, Support Vector Machine, SMOTE
Actions (login required)
 |
View Item |
