Identifying Patterns through Integration of Natural Language Processing and Semantic Web Technologies
Tatiana Vladimirovna Avdeenko, А. А. Golubnichiy · 2025
This chapter presents an exploration of natural language processing (NLP) analytical techniques and semantic web technologies for identifying structural and semantic patterns in text data. We review the core concepts of NLP, such as morphological, syntactic, and semantic analysis, and analyze key semantic web technologies, including RDF, OWL, and SPARQL, with a special focus on the role of ontologies in organizing and maintaining data. Machine learning techniques for pattern identification are discussed, including classification and clustering models, as well as time series analysis. It is substantiated how the use of ontologies and the fusion of data from different sources can improve the accuracy of text analysis. The proposed algorithm includes step-by-step instructions on how to use NLP libraries and semantic web technologies to identify patterns for NER tasks, as well as recommendations formulated for model optimization. The obtained results are analyzed, and prospects for further development and possible directions for future research are formulated, including ensuring the innovativeness of NLP and semantic web leaders to create more powerful and accurate tools for analyzing text data, opening up new opportunities for scientific research and practical applications.