Analysis of the efficiency of ontology-oriented approaches to business information extraction from unstructured web sources relating to aerospace production organization

Serhii Danov, Igor Shostak

Abstract


The subject of this research is ontology-oriented approaches to extracting business information from unstructured web sources. The aim of the article is to analyze the effectiveness of modern ontology-oriented approaches for extracting business information from unstructured web sources and to substantiate their feasibility for decision support systems. Such approaches are particularly important for the information and analytical support of aerospace enterprises, where activities require processing significant volumes of heterogeneous external information on cooperative relations, supplies, technical product support, regulatory requirements, and the market environment. Tasks include: analyzing the main challenges of collecting, mining, and processing business information from unstructured web sources; determining the feasibility of using ontologies to extract and integrate business information; and performing a comparative analysis of modern ontology-oriented approaches and identifying promising areas for future application. The study employed methods for analysis and generalization scientific sources, systems analysis, and comparative analysis, along with approaches to semantic and ontological modeling. The findings establish that the main factors complicating web-based business information extractions are the heterogeneity of data formats and structures, the ambiguity of natural language, the dynamism of the information environment, and the incompleteness or inconsistency of information. It is demonstrated that the use of ontologies enables the semantization, structuring, logical coordination, and integration of business information within a corporate knowledge base, while providing a foundation for improving the quality of analytical data processing. Modern ontology-oriented approaches are categorized into template-based methods, deep linguistic analysis, and machine learning. A comparative analysis reveals that hybrid approaches, which combine the advantages of various methodologies to ensure greater completeness, flexibility, and semantic consistency, are the most promising for decision support systems. Conclusions. The scientific novelty of the obtained results lies in the generalization and comparison of modern ontology-oriented approaches to extracting business information from unstructured web sources, considering their suitability for semantic data coordination, the formation of corporate knowledge bases, and their application in decision support systems.

Keywords


business information; unstructured web sources; ontology; information mining; semantic integration; corporate knowledge base; decision support systems

Full Text:

PDF

References


Hoseini, S., Theissen-Lipp, J., & Quix, C. A survey on semantic data management as intersection of ontology-based data access, semantic modeling and data lakes. Journal of Web Semantics, 2024, vol. 81, article no. 100819. DOI: 10.1016/j.websem.2024.100819.

Zeroual, S., Nessah, D., & Bakhouche, A. A systematic literature review on ontology-driven business intelligence components. The Electronic Journal of Knowledge Management, 2026, vol. 24, no. 1, pp. 101–118. DOI: 10.34190/ejkm.24.1.4277.

Xu, D., Chen, W., Peng, W., Zhang, C., Xu, T., Zhao, X., Wu, X., Zheng, Y., Wang, Y., & Chen, E. Large language models for generative information extraction: a survey. Frontiers of Computer Science, 2024, vol. 18, article no. 186357. DOI: 10.1007/s11704-024-40555-y.

Scannapieco, S., & Tomazzoli, C. Cnosso, a novel method for business document automation based on open information extraction. Expert Systems with Applications, 2024, vol. 245, article no. 123038. DOI: 10.1016/j.eswa.2023.123038.

Staudinger, S., Schütz, C. G., Schrefl, M., & Neuböck, T. Knowledge graph support for descriptive business analytics. Decision, 2025, vol. 52, no. 3, pp. 285–306. DOI: 10.1007/s40622-025-00432-4.

Arslan, M., Munawar, S., & Cruz, C. Business insights using RAG–LLMs: a review and case study. Journal of Decision Systems, 2024, pp. 1–30. DOI: 10.1080/12460125.2024.2410040.

Shim, M., Kim, H., Choi, Y., Kim, J., & Lee, J. OmEGa(Ω): Ontology-based information extraction framework for constructing task-centric knowledge graph from manufacturing documents with large language model. Advanced Engineering Informatics, 2025, vol. 64, article no. 103001. DOI: 10.1016/j.aei.2024.103001.

Amdouni, E., Belfadel, A., Gagnant, M., Renault, I., Kierszbaum, S., Carrion, J., Dussartre, M., & Tmar, S. Semi-Automatic Building of Ontologies from Unstructured French Texts: Industrial Case Study. Data Science and Engineering, 2025, vol. 10, no. 3, pp. 339–361. DOI: 10.1007/s41019-025-00284-z.

Mealey, K. P., Karr Jr, J. A., Moreira, P. S., Brenner, P. R., & Vardeman II, C. F. Trusted knowledge extraction for operations and maintenance intelligence. Natural Language Processing Journal, 2025, vol. 13, article no. 100187. DOI: 10.1016/j.nlp.2025.100187.

Zhao, X., Wang, R., Ren, S., Zhang, G., & Zhang, Y. A knowledge graph-driven framework of multi-stakeholder synergistic operation and maintenance for complex products: design, implementation and industrial validation. Advanced Engineering Informatics, 2025, vol. 68, article no. 103746. DOI: 10.1016/j.aei.2025.103746.

Liu, Z., Hu, B., Feng, Y., Lu, C., & Tan, J. Making manufacturing knowledge graph more intelligent: A knowledge intelligence management method for manufacturing enterprises. Advanced Engineering Informatics, 2026, vol. 71, article no. 104264. DOI: 10.1016/j.aei.2025.104264.

Yao, L., Ren, F., Du, K., & Du, Q. From knowledge graph construction to retrieval-augmented generation: a framework for comprehensive earthquake emergency support. Geo-spatial Information Science, 2025 vol. 29, no. 1, pp. 509–529. DOI: 10.1080/10095020.2025.2514813.

Golubeva, A. A rapid review on ontology- and data-driven business process modelling. New Trends in Computer Sciences, 2025, vol. 3, no. 2, pp. 83–99. DOI: 10.3846/ntcs.2025.24801.

Stănescu, G., & Oprea, S.-V. Recent Trends and Insights in Semantic Web and Ontology-Driven Knowledge Representation Across Disciplines Using Topic Modeling. Electronics, 2025, vol. 14, no. 7, article no. 1313. DOI: 10.3390/electronics14071313.

Muppasani, B. C., Gervet, C., & De Giacomo, G. Building a planning ontology to represent and exploit planning domain knowledge. Discover Artificial Intelligence, 2025, vol. 5, article no. 93. DOI: 10.1007/s44248-025-00093-9.

Scharpf, P. Entity linking with Wikidata: a systematic literature review. ACM Computing Surveys, 2024, vol. 56, no. 12, article no. 302, pp. 1–38. DOI: 10.1145/3617696.

Gohourou, D., & Kuwabara, K. Knowledge Graph Extraction of Business Interactions from News Text for Business Networking Analysis. Machine Learning and Knowledge Extraction, 2024, vol. 6, no. 1, pp. 126–142. DOI: 10.3390/make6010007.

Ambalavanan, R., Snead, R. S., Marczika, J., Towett, G., Malioukis, A., & Mbogori-Kairichi, M. Ontologies as the semantic bridge between artificial intelligence and healthcare. Frontiers in Digital Health, 2025, vol. 7, article no. 1668385. DOI: 10.3389/fdgth.2025.1668385.

Liu, H., Yang, S., Shi, G., & Miao, Z. Knowledge graph reasoning: Mainstream methods, applications and prospects. Engineering Applications of Artificial Intelligence, 2025, vol. 159, part B, article no. 111625. DOI: 10.1016/j.engappai.2025.111625.

Parsanasab, E., Ahmadipour, A., & Mehraeen, E. Utilization of Ontology to Develop Artificial Intelligence Systems in the Healthcare Industry. Healthc Inform Res, 2025, vol. 31, no. 4, pp. 320-330. DOI: 10.4258/hir.2025.31.4.320.

Hadji, A., & Kholladi, M. K. Disaster Information Extraction: Evaluation of NLP Techniques Using JAPE Rules, Ontologies and Machine Learning Approaches. In: Proceedings of the 3rd International Conference on Computer Science's Complex Systems and Their Applications, 2025, pp. 294–313. DOI: 10.1007/978-3-031-90758-6_22.

Yang, Y., Wu, Z., Yang, Y., Lian, S., Guo, F., & Wang, Z. A Survey of Information Extraction Based on Deep Learning. Applied Sciences, 2022, vol. 12, no. 19, article no. 9691. DOI: 10.3390/app12199691.




DOI: https://doi.org/10.32620/aktt.2026.2.11