This paper addresses the lack of a strategic framework for creating and combining ontologies in the peace and conflict studies field. Although this is an important area of study, not much attention has been given to ontology modeling here. To fill this gap, we propose a strategic and automated framework for synthesizing ontologies. Our framework starts by extracting information from the dataset and uses this information to create a feature feedback mechanism by referring to Wiki data and CYC Knowledge Store repositories. This feedback mechanism helps in classification tasks using SVM (Support Vector Machine). We also generate metadata and make the framework more adaptable using the Deep Belief Networks classifier. To measure semantic similarity, we use the SOC-PMI method, and for optimization purposes, we implement the Clonal Selection Principle, which is a meta-optimization strategy. Additionally, we use DBSCAN clustering to generate an initial seed ontology with strong associations. The proposed model achieves high percentages of precision, recall, accuracy, and F-measure, specifically 95.33%, 96.78%, 96.055%, and 96.04952787% respectively. Additionally, the model achieves a low value of FDR (False Discovery Rate) at 0.05% is achieved.