Assessment of University Students' Earthquake Coping Strategies Using Artificial Intelligence Methods

Abstract

Earthquakes are one of the most destructive natural disasters that pose a serious threat to human life and infrastructure worldwide. The aim of this study is to evaluate the coping strategies of adult individuals in Turkey regarding earthquake stress using artificial intelligence-based methods. The data was collected from 858 university students living in Turkey during January, February, and March 2024. A dataset was created using the 'Coping Scale for Earthquake Stress.' Prediction models were established using artificial intelligence algorithms such as Logistic Regression (LR), Bagging, and Random Forest (RF) based on information from 24 variables. The cross-validation method was applied during model training. The Logistic Regression algorithm achieved the highest accuracy rate of 98.60%, while the Bagging algorithm demonstrated the lowest performance with an accuracy rate of 79.95%. The Random Forest algorithm showed moderate performance with an accuracy rate of 85.89%. The findings provide important insights into the coping strategies of the community regarding earthquake stress. This study is expected to contribute significantly to areas such as disaster management, psychology, public health, and community resilience.