Constructing Co-Occurrence Graphs and Deriving Flood Ontologies for Enhanced Understanding
Sundos Nasser Said Al Subhi, Armin Robert Mikler, Mario Kubek · 2024
Developing ontologies traditionally requires significant expertise and time investment. The research study proposes an approach to automate the construction of flood ontologies from textual documents using Natural Language Processing (NLP) techniques and ontology learning. The research work presents an algorithm specifically designed to extract relevant concepts and relationships from flood-related documents, facilitating the automatic generation of ontologies. By constructing co-occurrence graphs and employing the proposed algorithm, the proposed approach aims to uncover implicit knowledge embedded within textual data, thus enhancing understanding and enabling more efficient ontology construction. The significance of this work lies in its potential to streamline the process of building flood ontologies, reducing the reliance on domain experts and accelerating the pace of ontology development. The proposed approach empowers researchers and practitioners to quickly identify key concepts and relationships relevant to flood management and research. This, in turn, can facilitate more effective decision-making and resource allocation in flood-prone areas.