COMPARISON OF BILSTM, SVM FOR PBB-P2 TAX POLICY SENTIMENT ANALYSIS
Abstract
Abstract: The policy to increase the Rural and Urban Land and Building Tax (PBB-P2) in Indonesia often elicits mixed reactions from the public. Some support it because they believe it can strengthen regional fiscal capacity, while others reject it because they are concerned that it will increase the economic burden on the community. Understanding public sentiment towards this policy is important for evaluating the effectiveness of the policy and formulating appropriate communication strategies. This study aims to analyze public sentiment towards the PBB-P2 increase policy using data uploaded on Platform X (Twitter). The data were collected through crawling with the keyword “building tax,” then processed through several preprocessing stages before classifying tweets into positive and negative sentiments. Two models were used: Support Vector Machine (SVM) and Bidirectional Long Short-Term Memory (BiLSTM). Results show that SVM outperformed BiLSTM, achieving training accuracy of 99.4% and testing accuracy of 85.9%, with accuracy 0.8595, precision 0.8536, recall 0.8595, and F1-score 0.8449. Meanwhile, BiLSTM achieved training accuracy of 86.9% and testing accuracy of 82.9%, with accuracy 0.8294, precision 0.8150, recall 0.8294, and F1-score 0.8080. These findings suggest SVM is more effective in classifying public sentiment and can support better evaluation of regional tax policies.
Keywords: sentiment analysis; PBB-P2; BiLSTM; SVM; X platform
Abstrak: Kebijakan kenaikan tarif Pajak Bumi dan Bangunan Perdesaan dan Perkotaan (PBB-P2) di In-donesia sering memunculkan beragam reaksi dari masyarakat. Sebagian mendukung karena dianggap dapat memperkuat kapasitas fiskal daerah, sementara lainnya menolak karena kha-watir menambah beban ekonomi masyarakat. Pemahaman terhadap sentimen publik atas ke-bijakan tersebut penting untuk mengevaluasi efektivitas kebijakan dan merumuskan strategi komunikasi yang tepat. Penelitian ini bertujuan menganalisis sentimen masyarakat terhadap kebijakan kenaikan PBB-P2 menggunakan data unggahan di Platform X (Twitter). Data dik-umpulkan melalui proses crawling dengan kata kunci “pajak bangunan” kemudian diproses melalui beberapa tahap preprocessing sebelum diklasifikasikan menjadi sentimen positif dan negatif. Dua model digunakan dalam penelitian ini, yaitu Support Vector Machine (SVM) dan Bidirectional Long Short-Term Memory (BiLSTM). Hasil penelitian menunjukkan bahwa SVM memiliki kinerja lebih baik dibandingkan BiLSTM, dengan akurasi pelatihan 99,4% dan akurasi pengujian 85,9%. Nilai akurasi 0,8595, precision 0,8536, recall 0,8595, dan F1-score 0,8449. Sementara itu, BiLSTM memperoleh akurasi pelatihan 86,9% dan akurasi pengujian 82,9%, dengan akurasi 0,8294, precision 0,8150; recall 0,8294; dan F1-score 0,8080. Temuan ini menunjukkan bahwa SVM lebih efektif dalam mengklasifikasikan sentimen publik serta dapat mendukung evaluasi kebijakan pajak daerah dengan lebih baik.
Kata kunci: analisis sentimen; PBB-P2; BiLSTM; SVM; platform X
References
C. Kansil, “Peran Hukum Pajak dalam Mendorong Pembangunan Ekonomi Nasional untuk Mewujudkan Tujuan Negara,” J. Multidisiplin Indones., vol. 3, no. 2, pp. 1655–1662, 2024.
V. Salsabella, C. Belina, N. S. Budiarso, and A. Wangkar, “Analisis pelaksanaan pemungutan Pajak Bumi Dan Bangunan Perdesaan dan Perkotaan (PBB - P2) berdasarkan Peraturan Bupati No 18 Tahun 2014 di Kecamatan Pasan Kabupaten Minahasa Tenggara,” vol. 2, no. 2, pp. 126–136, 2024, doi: 10.58784/ramp.123.
M. N. Huda and G. Wicaksono, “Analisis Efektivitas Dan Kontribusi Penerimaan Pajak Bumi Dan Bangunan Perdesaan Dan Perkotaan Terhadap Pendapatan Asli Daerah Kota Yogyakarta,” Educoretax, vol. 1, no. 4, pp. 284–290, 2021, doi: 10.54957/educoretax.v1i4.108.
E. P. Adamansyah and A. Yudhistira, “Evaluasi Opini Publik di Media Sosial X terhadap Kebijakan Pajak Pertambahan Nilai 12% di Indonesia Menggunakan Naive Bayes dan Decision Tree,” J. Pendidik. dan Teknol. Indones., vol. 5, no. 3, pp. 831–843, 2025, doi: 10.52436/1.jpti.710.
S. Asmara and F. I. Butsi, “Twitter dan Public Sphere: Studi Fenomenologi Tentang Twitter Sebagai Media Alternatif Komunkasi Politik,” J. Ilm. Ilmu Komun. Commun., vol. 2, no. 2, pp. 75–84, 2020, doi: 10.62144/jikq.v2i2.30.
R. Nursyanti, N. Alamsyah, and T. M. Yusuf, “Aisyah Journal of Informatics and Electrical Engineering,” Aisyah J. Informatics Electr. Eng., vol. 7, no. 1, pp. 137–145, 2025, [Online]. Available: http://jti.aisyahuniversity.ac.id/index.php/AJIEE
M. F. Amin, “Confusion matrix in three-class classification problems: A step-by-step tutorial,” J. Eng. Res., vol. 6, no. 5, 2023, [Online]. Available: https://erjeng.journals.ekb.eg/article_296718_30a98aac15193d04dc73ba9bc00cf046.pdf
A. Yudhistira, “Analisis Sentimen Petani Milenial Pada Media Sosial X Menggunakan Algortitma Support Vector Machine ( SVM ) Fakultas Teknik dan Ilmu Komputer , Universitas Teknokrat Indonesia , Indonesia Sentiment Analysis of Millennial Farmers on Social Media X Using th,” vol. 5, no. 3, pp. 845–857, 2025, doi: https://doi.org/10.52436/1.jpti.717.
P. Utami, M. R. Ningsih, D. Ananda, and A. Pertiwi, “Sentimen based-emotion classification using bidirectional long,” pp. 281–289, 2024, doi: https://doi.org/10.52465/joscex.v5i3.461.
P. Arsi, R. A. Firmanda, I. Prayoga, and P. Subarkah, “Opinion Mining on Spotify Music App Reviews Using Bidirectional LSTM and BERT,” vol. 11, no. 2, pp. 68–74, 2025.
P. Subarkah, H. A. A. Rozaq, P. Arsi, S. A. Sholikhatin, R. Riyanto, and H. Marcos, “Implementation of Text Mining to Detect Emotions of Fuel Price Increase using BERT-LSTM Methods,” Gazi Univ. J. Sci., vol. 37, no. 4, pp. 1707–1716, 2024, doi: 10.35378/gujs.1424742.
A. A. Rashifa, H. Marcos, P. Subarkah, and S. A. Sholikhatin, “Comparison of Svm and Naïve Bayes Classifier Algorithms on Student Interest in Joining Msib,” JITK (Jurnal Ilmu Pengetah. dan Teknol. Komputer), vol. 10, no. 1, pp. 116–123, 2024, doi: 10.33480/jitk.v10i1.5270.
P. Subarkah, B. A. Kusuma, and P. Arsi, “Sentiment Analysis on Renewable Energy Electric Using Support Vector Machine (Svm) Based Optimization,” JITK (Jurnal Ilmu Pengetah. dan Teknol. Komputer), vol. 10, no. 2, pp. 252–260, 2024, doi: 10.33480/jitk.v10i2.5575.
A. J. N. Kisma, P. Arsi, and P. Subarkah, “Sentiment Analysis Regarding Candidate Presidential 2024 Using Support Vector Machine Backpropagation Based,” JTAM (Jurnal Teor. dan Apl. Mat., vol. 8, no. 1, p. 96, 2024, doi: 10.31764/jtam.v8i1.17294.
D. Haliza and M. Ikhsan, “Sentiment Analysis on Public Perception of the Nusantara Capital on Social Media X Using Support Vector Machine (SVM) and K-Nearest Neighbor (K-NN) Methods,” J. Appl. Informatics Comput., vol. 9, no. 3, pp. 716–723, 2025, doi: 10.30871/jaic.v9i3.9318.
B. Omarov and Z. Zhumanov, “Bidirectional Long-Short-Term Memory with Attention Mechanism for Emotion Analysis in Textual Content,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 6, pp. 129–136, 2023, doi: 10.14569/IJACSA.2023.0140615.
