A CONCEPTUAL MODEL FOR ONTOLOGY-BASED DETECTION OF INFORMATION OPERATIONS IN DIGITAL MEDIA

With the rapid growth of disinformation, cognitive manipulation and coordinated information campaigns in digital media, there is a need to develop intelligent methods for identifying and analyzing information operations. This paper proposes a conceptual model that integrates a multilingual annotated corpus, an ontological knowledge base and a semantic knowledge graph for the systematic study of mechanisms of information impact.
The methodology of the research includes the construction of a specialized framework formed out of messages collected from Telegram channels, news portals and social networks. The data goes through a multi-level annotation using the Label Studio platform, where experts manually mark key entities, including military terms, target audiences, sources, actors, and emotional evaluations. The annotated corpus is semantically corresponded with the ontology of the subject field, formalized in OWL and enriched with the military thesaurus MIL_term, which provides consistency of terminology and support for multilingual analytics.
The ontological model is transformed into an RDF-graph of knowledge, reflecting the relationships between entities, events, tactics and narratives. SWRL-rules are used to identify hidden patterns, and the developed SPARQL-queries allow to extract complex analytical patterns, including chains of "actor – tactic – narrative – audience". The proposed approach forms the basis for complex analysis of information flows, early detection of threats and construction of analytical scenarios, which makes it applicable for research and monitoring of information operations in multilingual digital environments.

1. Abdali S. Multi-modal misinformation detection: Approaches, challenges and opportunities / S. Abdali, S. Shaham, B. Krishnamachari // ACM Computing Surveys. – 2024. – Vol. 57, № 3. – P. 1-29.

2. From Virality to veracity / J. Rieskamp et al // Examining False Information on Telegram vs. Twitter. – 2024.

3. Zhao J. et al. Research on domain ontology construction based on the content features of online rumors. – 2024. – Vol. 14, № 1. – P. 12134.

4. Detecting propaganda techniques in code-switched social media text / M.U. Salman et al // arXiv preprint arXiv:2305.14534. – 2023.

5. Alghamdi J. Fake news detection in low-resource languages: A novel hybrid summarization approach / J. Alghamdi, Y. Lin, S. Luo // Knowledge-based Systems. – 2024. – Vol. 296. – P. 111884.

6. The influence Operation Ontology (IOO) / A.D.C. Tudela et al // arXiv preprint arXiv:2503.07304. – 2025.

7. A common core-based cyber ontology in support of cross-domain situational awareness / B. Donohue et al // ground/air multisensor interoperability, integration, and networking for persistent ISR IX. – SPIE, 2018. – Vol. 10635. – P. 65-74.

8. Partridge C. digitalizing uncertain Information / C. Partridge, A. Mitchell, A. Cola //arXiv preprint arXiv:2507.21173. – 2025.

9. SOK: Come together–unifying Security, Information Theory, and cognition for a Mixed Reality deception attack Ontology & Analysis Framework / A. Teymourian et al // arXiv preprint arXiv:2502.09763. – 2025.

10. Zhang L., Lobov A. Semantic web rule language-based approach for implementing knowledgebased engineering systems. – 2024. – Vol. 62. – P. 102587.

11. Languages and systems for RDF stream processing, a survey / P. Bonte et al // The VLDB Journal. – 2025. – Vol. 34, № 4. – P. 50.