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

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.