Menggali Opini Publik: Sentimen Terhadap Kebijakan Makan Siang Gratis Dengan Supervised Learning

Penulis

  • Dwija Wisnu Brata Universitas Brawijaya, Malang
  • Welly Purnomo Universitas Brawijaya, Malang
  • Hariz Farisi Universitas Brawijaya, Malang
  • Henry Kevin Marcelino Ratu Universitas Brawijaya, Malang

DOI:

https://doi.org/10.25126/jtiik.2025129565

Kata Kunci:

free lunch opinion, supervised learning, sentiment, social media opinion

Abstrak

Di era informasi saat ini, opini publik menjadi aset penting dalam membentuk kebijakan sosial dan politik. Salah satu kebijakan yang sering menarik perhatian adalah program makan siang gratis yang ditujukan untuk meningkatkan kesejahteraan sosial. Kebijakan yang direncanakan bertujuan untuk memberikan manfaat bagi anak-anak di Indonesia agar dapat meningkatkan asupan gizi dan nutrisi, tetapi sering kali menimbulkan berbagai reaksi dari masyarakat, terutama di media sosial. Penelitian ini dilakukan untuk menggali sentimen berdasarkan opini tentang rencana kebijakan makan siang gratis oleh pemerintah Indonesia pada media sosial twitter. Total dataset yang dikumpulkan sebanyak 1359 yang telah di-preprocessing, terbagi atas 1000 sentimen negatif, dan 359 sentimen positif. Metode klasifikasi yang digunakan dan menjadi pembanding yaitu Support Vector Machine (SVM), Naïve Bayes (NB), dan Random Forest (RF). Hasil penelitian menunjukkan bahwa metode SVM memiliki tingkat akurasi yang lebih tinggi (85%) dibanding dua metode lainnya.

 

Abstract

In today's information technology era, public opinion is an important asset in shaping social and political policies. One policy that often attracts attention is the free lunch program aimed at improving social welfare. The planned policy aims to benefit children in Indonesia in order to improve their nutritional intake, but it often generates various reactions from the public, especially on social media. This study was conducted to explore opinion-based sentiment about the free lunch policy plan by the Indonesian government on social media Twitter. The total dataset collected was 1359 that had been cleaned, divided into 1000 negative sentiments, and 359 positive sentiments. The classification methods used for comparison are Support Vector Machine (SVM), Naïve Bayes (NB), and Random Forest (RF). The results show that the SVM method has a higher accuracy rate (85%) than the other two methods.

Downloads

Download data is not yet available.

Referensi

A. SAEPULROHMAN, S. SAEPUDIN AND D. GUSTIAN, 2021. Analisis Sentimen Kepuasan Pengguna Aplikasi WhatsApp Menggunakan Algoritma Naïve Bayes Dan Support Vector Machine privat maupun grup. In: is The Best Accounting Information Systems and Information Technology Business Enterprise this is link for OJS us.

ARDHANI, B.A., CHAMIDAH, N. AND SAIFUDIN, T., 2021. Sentiment Analysis Towards Kartu Prakerja Using Text Mining with Support Vector Machine and Radial Basis Function Kernel. Journal of Information Systems Engineering and Business Intelligence, [online] 7(2), p.119. https://doi.org/10.20473/jisebi.7.2.119-128.

BRATA, D.W. AND FARISI, H., 2023. Etalase Online Pedagang Produk UMKM dan Fashion Di Wilayah Kota Malang dalam Penerapan UMKM Berbasis Teknologi Menggunakan Information Retrieval. Jurnal Ilmiah Teknologi Informasi Asia, 17(2), p.109. https://doi.org/10.32815/jitika.v17i2.897.

BRATA, D.W., PURNOMO, W. AND NOFANDI, A., 2024. Extracting Customer Reviews of Restaurants to Explore Service Aspects on Google Review and Tripadvisor as Factors for Quality Improvement. Jurnal Ilmiah Teknologi Infomasi Asia.

CHAUHAN, P., 2017. Sentiment Analysis: A Comparative Study of Supervised Machine Learning Algorithms Using Rapid miner. International Journal for Research in Applied Science and Engineering Technology, [online] V(XI), pp.80–89. https://doi.org/10.22214/ijraset.2017.11011.

EKAWATI, I., SUMADYO, M. AND WHIDHIASIH, R.N., 2022. Analisa Sentimen Masyarakat Terhadap Kebijakan Pemerintah Selama Pandemi Covid-19 Menggunakan Support Vector Machine dan Naïve Bayes. JREC (Journal of Electrical and Electronics)

ISNAIN, A.R., SAKTI, A.I., ALITA, D. AND MARGA, N.S., 2021. Sentimen Analisis Publik Terhadap Kebijakan Lockdown Pemerintah Jakarta Menggunakan Algoritma Svm. Jurnal Data Mining dan Sistem Informasi, 2(1), p.31. https://doi.org/10.33365/jdmsi.v2i1.1021.

LIU, C., ZHONG, Q., AO, X., SUN, L., LIN, W., FENG, J., HE, Q. AND TANG, J., 2020. Fraud Transactions Detection via Behavior Tree with Local Intention Calibration. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. [online] New York, NY, USA: ACM. pp.3035–3043. https://doi.org/10.1145/3394486.3403354.

M, H. and M.N, S., 2015. A Review on Evaluation Metrics for Data Classification Evaluations. International Journal of Data Mining & Knowledge Management Process, 5(2), pp.01–11. https://doi.org/10.5121/ijdkp.2015.5201.

PADURARIU, C. and BREABAN, M.E., 2019. Dealing with data imbalance in text classification. In: Procedia Computer Science. Elsevier B.V. pp.736–745. https://doi.org/10.1016/j.procs.2019.09.229.

PAMUNGKAS, F.S. and KHARISUDIN, I., 2021. Analisis Sentimen dengan SVM. [online] 4, pp.628–634. Available at: <https://journal.unnes.ac.id/sju/index.php/prisma/>.

PISNER, D.A. and SCHNYER, D.M., 2020. Support vector machine. In: Machine Learning. Elsevier. pp.101–121. https://doi.org/10.1016/B978-0-12-815739-8.00006-7.

RAHAT, A.M., KAHIR, A. and MASUM, A.K.M., 2019. Comparison of Naive Bayes and SVM Algorithm based on Sentiment Analysis Using Review Dataset. In: 2019 8th International Conference System Modeling and Advancement in Research Trends (SMART). IEEE. pp.266–270. https://doi.org/10.1109/SMART46866.2019.9117512.

THARWAT, A., 2021. Classification assessment methods. Applied Computing and Informatics, 17(1), pp.168–192. https://doi.org/10.1016/j.aci.2018.08.003.

WIDIASTUTI, N.I., RAINARLI, E. and DEWI, K.E., 2017. Peringkasan dan Support Vector Machine pada Klasifikasi Dokumen. JURNAL INFOTEL, 9(4), p.416. https://doi.org/10.20895/infotel.v9i4.312.

WIRA YUDHA, S. and WAHYUDI, M., 2018. Komparasi Algoritma Klasifikasi Untuk Analisis Sentimen Review Film Berbahasa Asing. Sistem Informasi Dan Keamanan Siber (SEINASI-KESI) Jakarta-Indonesia

Diterbitkan

30-06-2025

Terbitan

Bagian

Ilmu Komputer

Cara Mengutip

Menggali Opini Publik: Sentimen Terhadap Kebijakan Makan Siang Gratis Dengan Supervised Learning. (2025). Jurnal Teknologi Informasi Dan Ilmu Komputer, 12(3), 533-538. https://doi.org/10.25126/jtiik.2025129565