An ontology is a representation model which defines domain knowledge with explicit specifications that feature interoperability between human and machine, thereby solving the problems of ambiguity and vagueness in knowledge sharing and reuse. Ontology construction is a lengthy, costly and controversial process. Hence, many studies in automatic ontology construction have emerged. In the processes of ontology construction, relations between concepts and the ways concepts are organized by their relations determine the ontology structure, which in turn affects the accuracy of domain knowledge. Consequently, concept relations exploration is the most important process of ontology construction. This study proposes a concept relation exploration approach that combines the characteristics of middle-out and top-down approaches in a process that resembles snowflakes crystallization. Based on the crystallizing concept exploration approach, this study implements an ontology construction mechanism that can automatically mine domain concepts out of domain document, determine relations between concept, and construct the domain ontology accordingly, thereby reducing cost and burden that would be incurred in a manual construction process.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Artificial Intelligence