A need for a strategic framework for tweet classification and recommendation has emerged, specifically for geographical catastrophes and events. This paper proposes a semantics-oriented model for disaster tweet classification in which the latent semantic indexing and WikiData are encompassed for topic modelling and auxiliary knowledge addition into the model. Event ontologies highlighting catastrophes also contribute to the information present in the framework. This model encompasses the DT classifier and the transformer classifier in order to classify the dataset and the metadata respectively. The metadata generation also enriches the framework’s knowledge. The framework uses Google’s Knowledge Graph API to generate knowledge graphs and a shuffling agent helps in shuffling the knowledge for diversifying the intermediate solutions. Twitter Semantic Similarity and Adaptive Pointwise Mutual Information (APMI) measures are strong semantics-oriented reasoning models used in the framework for semantic relatedness computation. Animal Migration Optimization which is a metaheuristic optimization framework is also used for the computation of the optimal solution. The paper has a precision of 96.54%, an overall accuracy of 97.02%, and the lowest FDR of 0.04, outperforming all the baseline models considered in this paper.