This dissertation presents the System for Ontology Learning and Extraction (SOLE) framework, which automates the construction of hazard-specific ontologies and facilitates disaster-related information extraction. The study addresses key challenges in knowledge representation, information retrieval, and decision-making for disaster management. The first contribution involves developing methodologies to automate hazard-specific ontology construction from disaster-related knowledge bases, improving structured knowledge extraction and organization. The second contribution is the implementation of a framework that utilizes computational techniques, including Machine Learning, Natural Language Processing, and Graph Theory, to develop hazard-specific ontologies. The third contribution focuses on comparing structured symbolic concepts extracted through automated ontology construction with non-symbolic concepts derived from chunk-level text analysis. Advanced text analysis techniques further enhance situational awareness by extracting meaningful insights from the content. The SOLE framework provides a foundation for the construction of hazard-specific ontologies and facilitates disaster-related information extraction; however, further development and optimization are required before it can be deployed as a user-ready system. Together, these contributions offer an integrated approach to disaster management, improving decision-making, knowledge representation, and information retrieval in crisis scenarios. The findings highlight the potential of automated hazard-specific ontologies, developed using ontology learning techniques, to improve disaster preparedness and response efforts, enabling quicker and more accurate reactions to emerging disaster events.