Constructing a subject-based ontology through the utilization of a semantic knowledge graph

• Published in: International journal of information technology (Singapore. Online) Vol. 16; no. 2; pp. 1063 - 1071
• Main Authors: Ta, Chien D. C., Tran, Thien Khai
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.02.2024; Springer Nature B.V
• Subjects: Artificial Intelligence; Computer Imaging; Computer Science; Image Processing and Computer Vision; Information retrieval; Knowledge representation; Machine Learning; Natural language processing; Original Research; Pattern Recognition and Graphics; Semantics; Software Engineering; Vision; Topic-oriented search; Topic-oriented ontology; Ontology; Knowledge graph
• ISSN: 2511-2104; 2511-2112
• DOI: 10.1007/s41870-023-01575-2

Currently, the use of ontology-based applications is the significant strategy adopted by researchers in various fields such as information extraction, information retrieval, question-answering systems, and others. Typically, applications that use ontologies have a greater level of accuracy compared to those that do not use ontologies. Creating a topic-oriented ontology (TOO) can pose a significant challenge for researchers and may require a substantial amount of time to accomplish. Despite the difficulties involved in creating a TOO, researchers are still actively seeking solutions for developing it, given its potential applicability to a wide range of areas, particularly for topic-driven research. The paper proposes utilizing natural language processing (NLP) to construct a TOO from a collection of scientific papers by creating topic trees and analyzing the semantic relationships between them. The ACM corpus was employed for testing the method, and it produced favorable outcomes in terms of precision.