Journals / Mehmet Akif Ersoy Üniversitesi Uygulamalı Bilimler Dergisi / 2022 / Cilt: 6 - Sayı: 1

Determination of Important Variables in Food Security Classification Using Random Forest

Gıda Güvencesi Düzeyi Sınıflandırılmasında Kullanılan Önemli Göstergelerin Random Forest Yöntemine Göre Belirlenmesi

Pages
68–77
Publication Date
2022-03-24
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Results indicated that 55.4% of households suffered from food insecurity, where 7.7% of them with moderate hunger and 13.8% of them with severe hunger.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Seasonal agricultural workers are the most disadvantaged group of work forces in terms of poverty even though they are significant contributors to the agricultural economy in Turkey.
📊
Key Findings & Data:Responses of seasonal apricot workers in Malatya to 18 questions of the Household Food Security Survey Module (HFSSM) were analyzed using the Random Forests (RF) algorithm (n = 65).
💡
Conclusion & Impact:Results indicated that 55.4% of households suffered from food insecurity, where 7.7% of them with moderate hunger and 13.8% of them with severe hunger.
🔬Design:Survey & Empirical Study
📍Scope:Comprehensive Sample
⚙️Variables:Gıda güvencesi · Random forest · HFSSM

Abstract

Seasonal agricultural workers are the most disadvantaged group of work forces in terms of poverty even though they are significant contributors to the agricultural economy in Turkey. The objectives of this study were to determine the food security status of seasonal agricultural workers and to determine the most important variables in the classification of household food security status for the seasonal agriculture workers. Responses of seasonal apricot workers in Malatya to 18 questions of the Household Food Security Survey Module (HFSSM) were analyzed using the Random Forests (RF) algorithm (n = 65). Results indicated that 55.4% of households suffered from food insecurity, where 7.7% of them with moderate hunger and 13.8% of them with severe hunger. The area under curve value of the RF model was estimated at 0.846 as the classification accuracy. The question “running out of food before having money to buy more” was the most important variable in the classification of the food security groups. Seasonal agricultural workers are prone to food insecurity and poverty due to low income and job insecurity in Turkey and in the world. Therefore, it is important to implement social aid programs to solve food insecurity issue in risk groups like seasonal agricultural workers.

Özet

Mevsimlik tarım işçileri, Türkiye'de tarım ekonomisine önemli katkılar sağlasalar da, yoksulluk açısından en dezavantajlı işgücü grubudur. Bu çalışmada mevsimlik tarım işçilerinin hane halkı gıda güvencesi durumlarının belirlenmesi ve gıda güvencesi sınıflandırmasına etki eden en önemli değişkenlerin belirlenmesi hedeflenmiştir. Malatya'da mevsimlik kayısı işçilerinin 18 sorudan oluşan Hanehalkı Gıda Güvencesi Anket Modülü (HFSSM) sorularına verdikleri yanıtlar Random Forest (RF) algoritması ile analiz edilmiştir (n = 65). Sonuçlar, hanehalklarının %55.4'ünün gıda güvencesiz olduğunu, bunlardan %7.7'sinin orta düzeyde, %13.8'inin ise ciddi düzeyde açlığın olduğu gıda güvencesizliği durumu yaşadıklarını göstermiştir. RF modelinin sınıflandırma doğruluğunu gösteren eğri altındaki alan değeri, 0.846 olarak tahmin edilmiştir. Gıda güvencesi gruplarının sınıflandırılmasında en önemli değişken “Daha fazla gıda alacak paraya sahip olmadan gıdanın bitmesi” sorusu olmuştur. Mevsimlik tarım işçileri, Türkiye'de ve dünyada düşük gelir ve iş güvencesizliği nedeniyle gıda güvencesizliği ve yoksulluk tehdidi altındadır. Bu nedenle mevsimlik tarım işçileri gibi risk gruplarında gıda güvencesizliği probleminin çözümüne yönelik sosyal yardım programlarının uygulanması önemlidir.

🔖

Cite This Article

EŞTÜRK, Ö. (2022). Determination of Important Variables in Food Security Classification Using Random Forest. Mehmet Akif Ersoy Üniversitesi Uygulamalı Bilimler Dergisi, Cilt: 6 - Sayı: 1, 68–77. https://ajindex.com/articles/790556

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (8)

  1. Anonymous. (2019).
  2. Global Food Security Index New York, USA: https://foodsecurityindex.eiu.com/.
  3. Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123-140. doi:10.1023/a:1018054314350 Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32. doi:10.1023/a:1010933404324 Breiman, L. (2004). Consistency for a simple model of random forests (Technical Report 670). California: University of California at Berkeley, https://www.stat.berkeley.edu/~breiman/RandomForests/consistencyRFA.pdf.
  4. Davison, K., & Kaplan, B. (2015). Food insecurity in adults with mood disorders: Prevalence estimates and associations with nutritional and psychological health. Annals of General Psychiatry, 14. doi:10.1186/s12991-015-0059-x Evans, J. S., Murphy, M. A., Holden, Z. A., & Cushman, S. A. (2011). Modeling Species Distribution and Change Using Random Forest. In Predictive Species and Habitat Modeling in Landscape Ecology (ss. 139-159). New York: Springer. FAO. (2002). The State of Food Insecurity in the World 2001. Erişim tarihi: March 14 2021, http://www.fao.org/3/y1500e/y1500e00.htm
  5. FAOSTAT. (2017). FAO Statistics. Erişim tarihi: March 15 2021, http://www.fao.org/faostat
  6. Fereli, S., Aktaç, Ş., & Güneş, F. E. (2016). Working conditions, nutritional status and problems seen on seasonal agricultural workers. Gazi Üniverstesi Sağlık Bilimleri Dergisi, 1(3), 36-47.
  7. Freund, Y., & Schapire, R. E. (1996). Experiments with a new boosting algorithm. Paper presented at the Proceedings of the Thirteenth International Conference on International Conference on Machine Learning, Bari, Italy. Godrich, S., K. Loewen, O., Blanchet, R., Willows, N., & Veugelers, P. (2019). Canadian Children from Food Insecure Households Experience Low Self-Esteem and Self-Efficacy for Healthy Lifestyle Choices. Nutrients, 11, 675. doi:10.3390/nu11030675 Grossmann, E., Ohmann, J., Kagan, J., May, H., & Gregory, M. (2010). Mapping ecological systems with a random forest model: Tradeoffs between errors and bias. Gap Analysis Bulletin, 17(1), 16-22.
  8. Gucciardi, E., Vogt, J. A., DeMelo, M., & Stewart, D. E. (2009). Exploration of the relationship between household food insecurity and diabetes in Canada. Diabetes care, 32(12), 2218-2224. doi:10.2337/dc09-0823 Heflin, C. M., Siefert, K., & Williams, D. R. (2005). Food insufficiency and women's mental health: Findings from a 3-year panel of welfare recipients. Social Science & Medicine, 61(9), 1971-1982. doi:https://doi.org/10.1016/j.socscimed.2005.04.