چكيده لاتين
The objective of the present research was to design and create a text-based ontology using a semi-automatic method in the field of logic, by leveraging generative AI platforms and utilizing unstructured informational texts. This research, focusing on the discussions of "terms" (Alfaz) within logic texts and with the aim of organizing concepts and conceptual relationships, was conducted within the framework of the Protégé software. The present study is applied in terms of purpose and descriptive in terms of approach. The research population included four primary books in the field of logic, and the research sample was the "Discussions on Terms" (Mabahith al-Alfaz) section from the book Al-Mantiq authored by Mohammad Reza Mazaher, which, in terms of its conceptual structure, covers the content of other primary sources in this field. Furthermore, four generative AI platforms, namely: DeepSeek, Gemini, Grok, and ChatGPT-5, and Visual Studio Code (based on GPT-4 and GPT-OSS), were employed in the data analysis process. The selection of sources and AI platforms was performed using purposive homogeneous sampling. The data collection tool was a researcher-made checklist based on the ontology structure, including classes, subclasses, relations, relation properties, and instances, and the data collection method was structured observation. For creating and modeling the ontology, Protégé software version 5.6.5 was used, and interaction with the generative AI platforms was carried out through Python coding within the Visual Studio Code environment. The findings indicated that the AI platforms were capable of detecting concepts (classes and subclasses) such as existence, term, signification, significate, types of signification, and types of existence; the relationships between concepts such as inclusion, type, signification, and opposition among them; and also the properties of relations, such as their being reflexive, non-reflexive, single-valued, transitive, or symmetric. Among the AI platforms, the Grok platform performed better across all stages of ontology formation in the field of logic .The results demonstrated that employing the semi-automatic method makes it possible to systematically extract the main concepts and their relationships from logic texts, particularly discussions on terms, and to organize these concepts within the framework of a coherent ontological structure. Furthermore, the semi-automatic approach, based on the integration of AI processing power and specialized human review, can provide an efficient and reliable method for designing ontologies in the field of logic, paving the way for the development of more advanced tools for information retrieval and conceptual analysis of logic texts.
