This paper presents Multi_mil, a multilingual annotated corpus designed for the analysis of information operations in military discourse. The corpus consists of 1000 texts collected from social media and news platforms in Russian, Kazakh, and English, covering military and geopolitical narratives. A multi-level annotation scheme was developed, combining entity categories (e.g., military terms, geographical references, sources) with pragmatic features such as information operation type, emotional tone, author intent, and fake claim indicators. Annotation was performed manually in Label Studio with high inter-annotator agreement ($\mathsf{\kappa }$ = 0.82). To demonstrate practical applicability, baseline models and the proposed Onto-IO-BERT architecture were tested, achieving superior performance (macro-F1 = 0.81). The corpus enables the identification of manipulation strategies, rhetorical patterns, and cognitive influence in multilingual contexts. Multi_mil contributes to advancing NLP methods for detecting disinformation, propaganda, and psychological operations.

The paper addresses the formal representation of knowledge about disinformation in a low-resource bilingual media environment. Automatic fake news detection is traditionally formulated as a binary REAL/FAKE classification task, which does not capture the internal structure of an unreliable message: the type of fake content, the disinformation technique employed, the author’s communicative intent, and the characteristics of the source and evidence base. Two interrelated resources are presented. The first is KazFakeCorpus, a bilingual corpus of 4,276 texts in Kazakh and Russian, balanced by class within each language; the REAL class was drawn from official materials of the Gov.kz portal and the FAKE class from their controlled transformations. The texts were annotated in Label Studio by two independent experts following a multi-level semantic scheme; Krippendorff’s Alpha for the principal levels ranged from 0.79 to 0.88. The second resource is KazFakeOnto, an ontology that recasts the annotation scheme from a flat relational representation into a formal OWL 2 DL model: 38 classes, 26 object properties, 22 data properties, 112 individuals and 1,155 asserted triples. Eleven defined classes are not asserted manually but inferred by a reasoner from property values; a property chain links a news item to its annotator through an annotation object. Consistency was verified with HermiT, and the query layer was evaluated on fifteen SPARQL and thirteen DL queries. The ontological layer is shown to provide a reproducible specification of the annotation scheme, the automatic inference of semantic categories, and a unified formal environment for formulating corpus-linguistic questions and analysing machine-learning model errors. The limitations of the approach and directions for scaling the ontology to the full corpus and to naturally occurring disinformation are discussed.

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.