Analisis Sentimen Publik Terhadap Polusi Udara di Kota Jakarta: Perbandingan Algoritma Support Vector Machine, Naive Bayes, dan Random Forest
Abstract
Air pollution in Jakarta has become a serious environmental issue, with pollutant concentrations such as PM2.5 and PM10 often exceeding safe limits, adversely affecting public health. This research analyzes public sentiment towards air pollution using machine learning algorithms: Support Vector Machine (SVM), Naive Bayes, and Random Forest. Data was collected from the social media platform Twitter through data crawling, with preprocessing steps such as cleaning, tokenizing, and stemming. The comparison of algorithm performance was conducted using accuracy, precision, recall, and F1-score metrics. The research results show that SVM has the highest accuracy at 91%, followed by Naive Bayes (85%) and Random Forest (81%). Public sentiment is dominated by negative opinions, reflecting concerns about the health impacts of air pollution. This study concludes that the SVM algorithm is the most effective for public sentiment analysis and can serve as a basis for the government in formulating more responsive and data-driven policies.
Keywords: Support Vector Machine; Naïve Bayes; Random Forest; Sentiment Analysis; Air Pollution
Abstrak
Polusi udara di Jakarta menjadi isu lingkungan serius dengan konsentrasi polutan seperti PM2.5 dan PM10 sering melebihi ambang batas aman, berdampak buruk pada kesehatan masyarakat. Penelitian ini menganalisis sentimen publik terhadap polusi udara menggunakan algoritma pembelajaran mesin: Support Vector Machine (SVM), Naive Bayes, dan Random Forest. Data diambil dari media sosial Twitter melalui crawling data, dengan proses preprocessing seperti cleaning, tokenizing, dan stemming. Perbandingan performa algoritma dilakukan menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa SVM memiliki akurasi tertinggi sebesar 91%, diikuti oleh Naive Bayes (85%) dan Random Forest (81%). Sentimen publik didominasi oleh opini negatif, mencerminkan kekhawatiran terhadap dampak kesehatan akibat polusi udara. Penelitian ini menyimpulkan bahwa algoritma SVM paling efektif untuk analisis sentimen publik dan dapat menjadi dasar bagi pemerintah dalam merumuskan kebijakan yang lebih responsif dan berbasis data.
Keywords
References
K. A. Arsyad and Y. Priyana, “Studi Kausalitas antara Polusi Udara dan Kejadian Penyakit Saluran Pernapasan pada Penduduk Kota Bogor, Jawa Barat, Indonesia,” J. Multidisiplin West Sci., vol. 2, no. 06, pp. 462–472, 2023.
S. Maharani and W. R. Aryanta, “Dampak Buruk Polusi Udara Bagi Kesehatan Dan Cara Meminimalkan Risikonya,” J. Ecocentrism, vol. 3, no. 2, pp. 47–58, 2023, doi: 10.36733/jeco.v3i2.7035.
S. Marlina, Dampak perubahan iklim pada kesehatan masyarakat. Penerbit NEM, 2022.
H. S. Alikodra and H. R. Syaukani, Global warming: banjir dan tragedi pembalakan hutan. Nuansa Cendekia, 2024. [Online]. Available: https://books.google.com/books? hl=en&lr=&id=LswDEQAAQBAJ&oi=fnd&pg=PA2&dq=tanah+musnah+ganti+rugi+negara+musibah&ots=eX_faHGVEV&sig=iNJ3HFgM7kwAGTpsEHLzsbSJnI8
Y. Akbar and T. Sugiharto, “Analisis Sentimen Pengguna Twitter di Indonesia Terhadap ChatGPT Menggunakan Algoritma C4. 5 dan Naïve Bayes,” J. Sains dan Teknol., vol. 5, no. 1, pp. 115–122, 2023.
D. Hidajat, Febry Gilang Tilana, and I Gusti Bagus Surya Ari Kusuma, “Dampak Polusi Udara terhadap Kesehatan Kulit,” Unram Med. J., vol. 12, no. 4, pp. 371–378, 2023, doi: 10.29303/jku.v12i4.1021.
A. Riyanto, A. Maheswara, R. Zulianty, V. M. Alegra, and ..., “Tanggung Jawab Pemerintah dalam Penyelesaian Masalah Polusi Udara di DKI Jakarta,” J. Pendidik. Tambusai, vol. 7, no. 3, pp. 27890–27896, 2023, [Online]. Available: https://www.jptam.org/index.php/jptam/ article/view/11232%0Ahttps://www.jptam.org/index.php/jptam/article/download/11232/8850
A. Amali, D. Maulana, E. Widodo, A. Firmansyah, and M. Danny, “The Sentiment Analysis of Bekasi Floods Using SVM and Naive Bayes with Advanced Feature Selection,” Brill. Res. Artif. Intell., vol. 4, no. 1, pp. 362–371, 2024.
Yoga Religia and A. Amali, “Perbandingan Optimasi Feature Selection pada Naïve Bayes untuk Klasifikasi Kepuasan Airline Passenger,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 5, no. 3, pp. 527–533, 2021, doi: 10.29207/resti.v5i3.3086.
A. C. Muhammad et al., Dasar-dasar Pembelajaran Mesin: (Foundations of Machine Learning), no. March. Sada Kurnia Pustaka, 2023. [Online]. Available: https://books.google.co.id/books?id=8COzEAAAQBAJ
Riduwan, Pengantar Statistik Sosial. Alfabeta. Penerbit Mafy, 2012.
N. F. Prih Waryatno, N. P. Kinanti, and Taryono, “Kondisi Pencemaran Udara pada Saat Periode Lebaran 2022 di Wilayah Jakarta,” Bul. GAW Bariri, vol. 3, no. 2, pp. 25–31, 2022, doi: 10.31172/bgb.v3i2.68.
B. H. Dhani Wahyu Wicaksono, “Analisis Sentimen Twitter Terhadap Kualitas Udara Jakarta Menggunakan Metode NBC,” J. Ilm. Elektron. DAN Komput., vol. 17, no. 03, pp. 103–110, 2023, doi: https://doi.org/10.51903/elkom.v17i1.1593.
A. Al Kaafi, Suparni, and H. Rachmi, “Analisis Opini Masyarakat Terhadap Pemberlakuan ERP Di Jalan Ibu Kota Jakarta,” J. Tek. Inform. dan Sist. Inf., vol. 11, no. 1, pp. 1–11, 2024.
L. Hakim, M. V. Dalimunthe, C. Danuputri, and D. Widyaningrum, “Sentimen Analisis Mengenai Polusi Udara Menggunakan Algoritma Support Vector Machine dan Random Forest,” J. Ilm. FIFO, vol. 15, no. 2, pp. 91–101, 2024, doi: 10.22441/fifo.2023.v15i2.001.
R. Kurniawan, A. Halim, and H. Melisa, “Prediksi Hasil Panen Pertanian Salak di Daerah Tapanuli Selatan Menggunakan Algoritma SVM (Support Vector Machine),” KLIK Kaji. Ilm. Inform. dan Komput., vol. 4, no. 2, pp. 903–912, 2023, doi: 10.30865/klik.v4i2.1246.
A. Nugroho and N. T. Kurniadi, “Journal of Computer Networks , Architecture and High Performance Computing Sentiment Analysis of Starlink on Twitter Using Support Vector Machine Algorithm Journal of Computer Networks , Architecture and High Performance Computing,” J. Comput. Networks, Archit. High Perform. Comput., vol. 6, no. 3, pp. 1321–1332, 2024, doi: https://doi.org/10.47709/cnapc.v6i3.4348.
A. D. Wibisono, S. Dadi Rizkiono, and A. Wantoro, “Filtering Spam Email Menggunakan Metode Naive Bayes,” TELEFORTECH J. Telemat. Inf. Technol., vol. 3 (4), no. 1, 2023, doi: 10.33365/tft.v1i1.685.
V. Jackins, S. Vimal, M. Kaliappan, and M. Y. Lee, “AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes,” J. Supercomput., vol. 77, no. 5, pp. 5198–5219, 2021, doi: 10.1007/s11227-020-03481-x.
M. Aria, C. Cuccurullo, and A. Gnasso, “A comparison among interpretative proposals for Random Forests,” Mach. Learn. with Appl., vol. 6, no. January, p. 100094, 2021, doi: 10.1016/j.mlwa.2021.100094.
M. Schonlau and R. Y. Zou, “The random forest algorithm for statistical learning,” Stata J., vol. 20, no. 1, pp. 3–29, 2020, doi: 10.1177/1536867X20909688.
D. W. Wicaksono and B. Hartono, “Analisis Sentimen Twitter Terhadap Kualitas Udara Jakarta Menggunakan Metode NBC,” J. Ilm. Elektron. DAN Komput., vol. 17, no. 1, pp. 103–110, 2024.
How To Cite This :
Refbacks
- There are currently no refbacks.
