Metode Classifier Gaussian Naïve Bayes Untuk Klasifikasi Konsumsi Makanan Cepat Saji Pada Tingkat Resiko Obesitas

Agus  Nursikuwagus; Suherman Suherman

doi:10.30656/jsii.v12i2.10650

Authors

Agus Nursikuwagus Universitas Komputer Indonesia
Suherman Suherman Universitas Komputer Indonesia

DOI:

https://doi.org/10.30656/jsii.v12i2.10650

Abstract

The increasing prevalence of obesity, particularly among adolescents, has become a significant public health concern. Main contribution factors are the excessive consumption of fast food, which is often high in calories, fats, sodium, and sugar. This shift in dietary habits is largely leveraged by globalization, which promotes a more convenient yet unhealthy lifestyle. In response to this issue, this study focuses on the designation of fast-food consumption based on nutrition facts, specifically employing data from McDonald’s menu items. The primary goal is to identify consumption patterns and predict whether a particular is at liability of dynamic obesity. This research utilizes the Gaussian Naïve Bayes (GNB) classification algorithm, implemented using the Python programming language. The dataset consists of 500 entries containing nutritional information such as calories, cholesterol, sodium, carbohydrates, sugars, protein, vitamins, calcium, fat, iron, fiber, potassium, minerals, and condition labels indicating obesity risk. The data was carved into training and testing sets, with 20% (100 data points) allocated for testing to assess the conduct of the model. The results of the experiment show that the GNB algorithm achieved an accuracy of 61%. For comparison, other machine learning models were also tested: Random Forest (RF) reach out the accuracy at 68%, succeeded by Multinomial Naïve Bayes at 65%, Support Vector Machine (SVM) and Decision Tree (DT) both at 62%. GNB showed limitations in predicting the TRUE class (indicating obesity risk), with a precision score of 60% and recall of 61%. These results suggest that the dataset distribution and the learning characteristics of GNB contributed to its relatively lower performance. Among the tested models, Random Forest demonstrated the best predictive capability, achieving a TRUE class precision of 76%, significantly outperforming GNB. This indicates that Random Forest is more reliable for classifying obesity risk based on fast food nutritional content. As a direction for future work, improvements can be made by tuning the parameters of the Random Forest model and exploring the application of deep learning techniques to further enhance predictive performance and generalizability.

Keywords: Classifier, Gaussian Naive Bayes, Klasifikasi, Preprocessing, Modeling, Good Health and Well-being.

References

[1] A. E. Puspa, "Strategi Pengembangan Bisnis Produk Fried Chicken D’besto Di Pt Setyanda Duta Makmur," Skripsi, Fakultas Sains dan Teknologi, UIN Syarif Hidayatullah Jakarta, 2019.

[2] U. Zein dan E. El Newi, Buku Ajar Ilmu Kesehatan (Memahami Gejala, Tanda Dan Mitos), Yogyakarta: Deepublish, 2019.

[3] R. Nurdiansyah, "Budaya Pola Konsumsi Makanan Cepat Saji Dalam Kehidupan Remaja Jakarta (Studi Kasus: Franchise KFC)," Skripsi, Fakultas Ilmu Sosial dan Ilmu Politik, UIN Jakarta, 2019.

[4] R. Muzakki, "Hubungan Konsumsi Makanan Cepat Saji Terhadap Peningkatan Risiko Obesitas Pada Anak Di Amerika Serikat."

[5] L. Mulyana dan E. Farida, "Pola Pemberian Makan Yang Tepat Dalam Mengurangi Resiko Obesitas Pada Balita," Indonesian Journal of Public Health and Nutrition, vol. 2, no. 1, hlm. 36–42, 2022.

[6] F. Z. Salsabila dan S. D. Puspowati, "Hubungan Konsumsi Fast Food Dengan Status Gizi Pada Remaja Di SMA Negeri 1 Kota Surakarta," Disertasi, Universitas Muhammadiyah Surakarta, 2022.

[7] N. U. Tanjung, A. P. Amira, N. Muthmainah, dan S. Rahma, "Junk Food Dan Kaitannya Dengan Kejadian Gizi Lebih Pada Remaja," Jurnal Ilmiah Kesehatan Masyarakat, vol. 14, no. 3, hlm. 133–140, 2022.

[8] T. Khoirunnisa dan R. Kurniasari, "Pengaruh Edukasi Melalui Media Pada Kejadian Overweight Dan Obesitas: Literature Review," Prepotif: Jurnal Kesehatan Masyarakat, vol. 6, no. 2, hlm. 1212–1217, 2022.

[9] M. Pakpahan, dkk., Pengantar Kesehatan Masyarakat, Yayasan Kita Menulis, 2022.

[10] W. Kusmawati, L. Lufthansa, R. S. Sari, dan S. M. Windriyani, Buku Ajar Ilmu Gizi Olahraga, Uwais Inspirasi Indonesia, 2019.

[11] A. Senika, R. Rasiban, dan D. Iskandar, "Implementasi Metode Naïve Bayes Dalam Penilaian Kinerja Sales Marketing Pada Pt. Pachira Distrinusa," Jurnal Media Informatika Budidarma, vol. 6, no. 1, hlm. 701–709, 2022.

[12] M. Muhajriah, "Analisis Penerapan Sistem Klasifikasi Dewey Decimal Classification (DDC) Di Dinas Perpustakaan Dan Kearsipan Kabupaten Enrekang," Disertasi, Universitas Islam Negeri Alauddin Makassar, 2020.

[13] M. Rumra, Y. Pasoreh, dan R. Lesnusa, "Pengaruh Penentuan Nomor Klasifikasi Terhadap Temu Kembali Informasi Bagi Pemustaka Di Perpustakaan Universitas Muhammadiyah Maluku Utara," Acta Diurna Komunikasi, vol. 2, no. 4, 2020.

[14] P. A. Mulyani, N. W. A. Sudiartini, dan N. L. P. Sariani, "Perilaku Masyarakat Kota Denpasar Dalam Mengkonsumsi Makanan Cepat Saji (Fast Food)," Juima: Jurnal Ilmu Manajemen, vol. 10, no. 2, 2020.

[15] H. N. Putri, H. Nisyak, dan G. L. Elake, "Food Globalization: Dampak Kudapan Fast Food Terhadap Eksistensi Kuliner Khas Kota Palembang," Disertasi, Universitas Sriwijaya, 2021.

[16] E. R. Eriska, A. K. Sari, dan L. N. Hakim, "Pengaruh Sistem Pelayanan, Kualitas Produk Terhadap Peningkatan Penjualan Di Restoran Cepat Saji Burger King," Kalianda Halok Gagas, vol. 5, no. 1, hlm. 14–22, 2022.

[17] D. P. Delima dan R. T. Prasetio, "Sistem Pakar Diagnosa Komplikasi Obesitas Pada Remaja Menggunakan Metode Certainty Factor," Eprosiding Sistem Informasi (Potensi), vol. 2, no. 1, hlm. 54–60, 2021.

[18] A. Darmawan, "Pengaruh Aktivitas Fisik Dan Pola Makan Sebagai Intervensi Penurunan Berat Badan Pada Anak Dengan Obesitas," Disertasi, Universitas Dr. Soebandi, 2022.

[19] S. R. Amanda, "Hubungan Aktivitas Fisik Terhadap Obesitas Pada Anak Usia Dini."

[20] N. M. J. S. N. Arini, "Hubungan Aktivitas Fisik Dengan Kejadian Obesitas Pada Remaja," 2020.

[21] W. M. Wahid dan M. B. Arimbi, "Pengaruh Latihan Aerobik Terhadap Penurunan Ketebalan Lemak Subkutan," Riyadhoh: Jurnal Pendidikan Olahraga, vol. 4, no. 2, hlm. 63–70, 2022.

[22] S. Manggabarani, A. J. Hadi, dan S. Ishak, "Edukasi Aktivitas Fisik Dalam Pencegahan Obesitas Di Madrasah Tsanawiyah Aisyiyah Kota Binjai," Jurnal Pengabdian Masyarakat Ilmu Kesehatan, vol. 1, no. 1, hlm. 1–6, 2020.

[23] E. E. Mawarni, "Perubahan Fisiologis Yang Berhubungan Dengan Aspek Gizi Dan Pengaruhnya Pada Status Gizi Lansia," Gizi Dalam Daur Kehidupan, vol. 4.2, hlm. 35, 2022.

[24] E. Indrayuni, "Klasifikasi Text Mining Review Produk Kosmetik Untuk Teks Bahasa Indonesia Menggunakan Algoritma Naive Bayes," Jurnal Khatulistiwa Informatika, vol. 7, no. 1, 2019.

[25] A. Wanto, dkk., Data Mining: Algoritma Dan Implementasi, Yayasan Kita Menulis, 2020.

[26] R. Amelia, D. Darmansah, N. S. Prastiwi, dan M. E. Purbaya, "Implementasi Algoritma Naive Bayes Terhadap Analisis Sentimen Opini Masyarakat Indonesia Mengenai Drama Korea Pada Twitter," Jurikom: Jurnal Riset Komputer, vol. 9, no. 2, hlm. 338–343, 2022.

[27] N. A'ayunnisa, Y. Salim, dan H. Azis, "Analisis Performa Metode Gaussian Naïve Bayes Untuk Klasifikasi Citra Tulisan Tangan Karakter Arab," Indonesian Journal of Data and Science, vol. 3, no. 3, hlm. 115–121, 2022.

[28] S. A. Firdaus, "Prediksi Penyakit Diabetes Dengan Metode Hyperbolic Support Vector Machine," Disertasi, Universitas Komputer Indonesia, 2020.

[29] M. F. R. Maula, "Automated Valuation Model Untuk Estimasi Nilai Pasar Rumah Berbasis Jaringan Saraf Tiruan Backpropagation," Disertasi, UIN Sunan Ampel Surabaya, 2022.

[30] R. Prathivi dan S. Sharifzadeh, "Performance Evaluation of Naive Bayes Algorithm for Classification of Fertilizer Types," Telematika, vol. 15, no. 1, hlm. 57–69, Feb. 2022.

[31] U. Modeling dan G. I. Webb, "Using Decision Trees for Agent Modeling: Improving Prediction Performance," Mar. 1998.

[32] J. Liang, "Confusion Matrix: Machine Learning," POGIL Activity Clearinghouse, vol. 3, no. 4, 2022.

[33] M. Heydarian, T. E. Doyle, dan R. Samavi, "MLCM: Multi-label Confusion Matrix," IEEE Access, vol. 10, hlm. 19083–19095, 2022.

[34] R. Yadav dan H. Raheman, "Machine Learning-based Estimation of Agricultural Tyre Sinkage: A Streamlit Web Application," J. Terramechanics, vol. 119, p. 101055, 2025.