Socio-economic impact of 2023 Turkey earthquake price hikes: insightful analysis using transformer models and XAI models

Abstract

Natural disasters like the 2023 earthquake in Turkey have significant social and economic effects, making it important to use analytical methods for creating strong, disaster-ready communities. In our work, we analyze public sentiment on social media after the earthquake, focusing on the rise in prices that followed. We classify public reactions into three categories: negative, positive, and neutral. To do this, we use several machine learning models, deep learning models, and two transformer based models. By analyzing the connection between people’s feelings and socio-economic factors like consumer spending, inflation, and price hikes, we aim to understand how public sentiment relates to policy decisions made in response to the crisis. Among all models tested, modified DistilBERT stood out, delivering the best performance with an accuracy of 82.20% and an F1-score of 84.30%. This shows that transformer-based models, particularly DistilBERT, are highly effective for sentiment analysis in this context. DistilBERT’s strong precision, recall, and F1-score suggest that it could be a valuable tool for informing policy changes to reduce the socio-economic impacts of natural disasters. Additionally, we used Explainable AI to help explain the model’s results, ensuring that policymakers can make informed decisions based on the data. Our research highlights the importance of advanced natural language processing (NLP) techniques for developing evidence-based policies in disaster management.