Bireylerin Çevresel Tutumlarını Tahminde Makine Öğrenmesi: ANOVA ve Ki-Kare Temelli Özellik Seçimi ile Algoritma Performanslarının Karşılaştırılması

Öz

Bu çalışma, bireylerin çevresel tutumlarının makine öğrenmesi (MÖ) yöntemleriyle tahmin edilmesine yönelik veri odaklı bir model geliştirmeyi amaçlamaktadır. Çalışmada, çevresel farkındalık düzeylerinin sınıflandırılmasına yönelik beş farklı MÖ algoritmasının (Destek Vektör Makineleri, Gradyan Artırma (GA), Çok Katmanlı Algılayıcı, Kuadratik Diskriminant Analizi ve Torbalama) performansı karşılaştırılmıştır. Model oluşturma sürecinde, veri setindeki değişkenlerin sınıflandırma başarısına etkisini belirlemek amacıyla tek yönlü varyans analizi (ANOVA) ve Ki-Kare Bağımsızlık Testi gibi istatistiksel yöntemler uygulanmıştır. Deneysel sonuçlar, ANOVA ve Ki-Kare tabanlı özellik seçimi süreçlerinin model başarımını artırmada etkili olduğunu göstermektedir. Özellikle GA algoritması, doğruluk, kesinlik ve F1 skoru bakımından diğer yöntemlere kıyasla üstün performans sergilemiştir. Elde edilen bulgular, MÖ algoritmalarının çevresel tutumların modellenmesi ve tahmin edilmesinde güçlü bir analitik çerçeve sunduğunu ortaya koymaktadır. Çalışma, çevresel farkındalık düzeylerinin veri odaklı yöntemlerle değerlendirilmesinin, sürdürülebilir çevre politikalarının geliştirilmesine ve bireylerin çevre bilincinin artırılmasına katkı sağlayacağını ortaya koymaktadır.

Anahtar Kelimeler

• çevresel tutum
• özellik seçimi
• makine öğrenmesi
• sürdürülebilirlik

Predicting Individuals' Environmental Attitudes Using Machine Learning: Comparison of Algorithm Performances with ANOVA and Chi-Square-Based Feature

Öz

This study aims to develop a data-driven model to predict individuals' environmental attitudes based on machine learning (ML) algorithms. The study compares the performance of five different ML algorithms—Support Vector Machines, Gradient Boosting (GB), Multilayer Perceptron, Quadratic Discriminant Analysis, and Bagging—in classifying environmental awareness levels. During the model development process, statistical methods such as one-way analysis of variance (ANOVA) and the Chi-Square Independence Test were applied to assess the impact of variables on classification accuracy. Experimental results indicate that ANOVA- and Chi-Square-based feature selection processes effectively enhance model performance. In particular, the GB algorithm outperforms others in terms of accuracy, precision, and F1 score. The findings demonstrate that ML algorithms provide a robust analytical framework for modelling and predicting environmental attitudes. This study highlights the significance of evaluating environmental awareness levels through data-driven approaches, contributing to the development of sustainable environmental policies and the enhancement of individuals' environmental consciousness.

Anahtar Kelimeler

• environmental attitude
• feature selection
• machine learning
• sustainability

Kaynakça

1. [1] R. L. Singh and P. K. Singh, "Global Environmental Problems," in Principles and Applications of Environmental Biotechnology for a Sustainable Future, R. Singh, Ed., Applied Environmental Science and Engineering for a Sustainable Future. Singapore: Springer, 2017, pp. 23-45.
2. [2] J. E. Hardoy, D. Mitlin, and D. Satterthwaite, “Environmental Problems in Third World Cities”. London: Taylor & Francis, 2024.
3. [3] N. Koklu and S. A. Sulak, "Classification of Environmental Attitudes with Artificial Intelligence Algorithms," Intelligent Methods in Engineering Sciences, vol. 3, no. 2, pp. 54-62, 2024.
4. [4] S. Çelik, "The effects of climate change on human behaviors," Environment, Climate, Plant and Vegetation Growth, pp. 577-589, 2020.
5. [5] M. Ahmadi and M. B. Tahoori, "Dynamic reconfigurable IoT security: Challenges and opportunities," Proc. IEEE, vol. 106, no. 1, pp. 72-86, 2018.
6. [6] X. Guo, K. Huang, and J. Lach, "Energy-adaptive cryptographic solutions for energy-harvesting IoT devices," IEEE Trans. Circuits Syst. I: Regular Papers, vol. 63, no. 5, pp. 629-638, 2016.
7. [7] L. F. Beiser-McGrath and R. A. Huber, "Assessing the relative importance of psychological and demographic factors for predicting climate and environmental attitudes," Climatic Change, vol. 149, pp. 335-347, 2018.
8. [8] A. Değirmenci, "Comparison of K-Nearest Neighbors, Decision Tree and Support Vector Machines Methods in Predicting Environmental Attitudes," Emerging Trends in Electrical and Electronics Engineering, vol. 4, 2024.

9. [9] N. Choudhury, R. Mukherjee, R. Yadav, Y. Liu, and W. Wang, "Can machine learning approaches predict green purchase intention? - A study from Indian consumer perspective," Journal of Cleaner Production, vol. 456, p. 142218, 2024.
10. [10] D. Amangeldi, A. Usmanova, and P. Shamoi, "Understanding Environmental Posts: Sentiment and Emotion Analysis of Social Media Data," IEEE Access, vol. 12, pp. 12345-12356, 2024.
11. [11] A. A. Takshe, M. Hennawi, S. E. Jebril, S. Alawi, S. AlZaidan, and A. Okasha, "Investigating determinants of pro-environmental behaviors amongst UAE university students through Q-methodology," Discover Sustainability, vol. 4, no. 1, p. 38, 2023.
12. [12] Q. Wang, Z. Kou, X. Sun, S. Wang, X. Wang, H. Jing, and P. Lin, "Predictive analysis of the pro-environmental behavior of college students using a decision-tree model," Int. J. Environ. Res. Public Health, vol. 19, no. 15, p. 9407, 2022.
13. [13] X. Lou, Y. Lin, and L. M. W. Li, "Predicting priority of environmental protection over economic growth using macroeconomic and individual-level predictors: Evidence from machine learning," J. Environ. Psychol., vol. 82, p. 101843, 2022.
14. [14] C. Li, L. Li, J. Zheng, J. Wang, Y. Yuan, Z. Lv, ... and W. Liu, "China’s public firms’ attitudes towards environmental protection based on sentiment analysis and random forest models," Sustainability, vol. 14, no. 9, p. 5046, 2022.
15. [15] Z. Kadiroğlu, E. Deniz, and A. Şenyiğit, "A comparison of deep learning models for pneumonia detection from chest x-ray images," J. Faculty Eng. Architect. Gazi Univ., vol. 39, no. 2, pp. 729-740, 2024.
16. [16] İ. Ş. Yapıcı, R. U. Arslan, ve O. Erkaymaz, "Kalp Yetmezliği Tanılı Hastaların Hayatta Kalma Tahmininde Topluluk Makine Öğrenme Yöntemlerinin Performans Analizi," Karaelmas Fen ve Mühendislik Dergisi, vol. 14, no. 1, pp. 59-69, 2024.
17. [17] E. I. Elsedimy, S. M. AboHashish, and F. Algarni, "New cardiovascular disease prediction approach using support vector machine and quantum-behaved particle swarm optimization," Multimedia Tools Appl., vol. 83, no. 8, pp. 23901-23928, 2024.
18. [18] A. Villar and C. R. V. de Andrade, "Supervised machine learning algorithms for predicting student dropout and academic success: a comparative study," Discover Artificial Intelligence, vol. 4, no. 1, pp. 2, 2024.
19. [19] B. Shankarlal, S. Dhivya, K. Rajesh, and S. Ashok, "A hybrid thyroid tumor type classification system using feature fusion, multilayer perceptron and bonobo optimization," Journal of X-Ray Science and Technology, Preprint, pp. 1-25, 2024.
20. [20] S. M. Malakouti, M. B. Menhaj, and A. A. Suratgar, "Machine learning and transfer learning techniques for accurate brain tumor classification," Clinical eHealth, vol. 7, pp. 106-119, 2024.
21. [21] D. V. Nguyen, J. Park, H. Lee, T. Han, and D. Wu, "Assessing industrial wastewater effluent toxicity using boosting algorithms in machine learning: A case study on ecotoxicity prediction and control strategy development," Environmental Pollution, vol. 341, p. 123017, 2024.
22. [22] R. Janković Babić, "A comparison of methods for image classification of cultural heritage using transfer learning for feature extraction," Neural Computing and Applications, vol. 36, no. 20, pp. 11699-11709, 2024.