A Decision Support System for Extracting Artificial Intelligence Driven Insights on Natural Disasters

Natural disasters present major obstacles to global disaster management initiatives and the potential for integrating Artificial Intelligence (AI) techniques into disaster management decision-support systems in order to overcome the drawbacks of traditional methods is enormous. One of the most important approaches to overcoming the obstacles is to assess Twitter data by utilizing AI technologies. By creating an AI-based Decision Support System (DSS) especially suited for Twitter data analysis, this research aims to bridge a significant gap in existing disaster management technologies. During catastrophic events, social media platforms—especially Twitter—have proved to be essential sources of timely and precise data. But, data from networking platforms is chaotic, which presents problems for conventional decision support systems. This research aims to improve the performance of disaster response as well as post disaster recovery by utilizing cutting-edge methods like LSTM (Long Short-Term Memory) networks and sentiment analysis libraries like TextBlob. The decision-makers and rescue workers can gain important insights by carefully examining the data to understand popular views and sentiments. This research intends to aid in the creation of more resilient and adaptable disaster management frameworks by utilizing AI techniques. A remarkable result of our approach using tweets data is the 97.5% of sensitivity estimation accuracy. Due to its high level of accuracy, Twitter data may provide strong and reliable insights which provide rescue executives and managers timely and accurate data during high-risk occurrences.