Список литературы

2518-1092

Research result. Information technologies

2518-1092

10.18413/2518-1092-2026-11-1-0-6

4100

ARTIFICIAL INTELLIGENCE AND DECISION MAKING

<strong>CONSTRUCTING MULTI-DOMAIN KNOWLEDGE SYSTEMS BASED ON MULTI-LAYER KNOWLEDGE GRAPHS</strong>

Pimeshkov

Vadim Konstantinovich

Pimeshkov

Vadim Konstantinovich

v.pimeshkov@ksc.ru

2026

11100

Knowledge systems enable the representation and application of structured information to solve a wide variety of problems. The development and application of modern knowledge systems inevitably encounter heterogeneous data, multiple stakeholders, or the support of multiple objectives. To address these challenges, the development of multidomain knowledge systems capable of coherently working with multiple domains within a single system becomes essential. This paper proposes the concept of multidomain knowledge systems, which describes knowledge systems operating in such conditions. Various examples of approaches to constructing knowledge systems that exhibit multidomain behavior in one way or another are considered. Topic modeling, in particular dynamic topic modeling, is considered as a basis for identifying layers in multilayer knowledge graphs. A multilayer dynamic knowledge graph (MDKG) concept is proposed, which uses a drifting dynamic topic model for layering, also allowing for tracking the emergence of new topics and the extinction of old ones. It is assumed that such a MDKG can be used to determine the relevance of text documents in the context of social media monitoring.

knowledge systemsknowledge graphssocial mediarelevance

Список литературы

Anton K. Topic modeling of natural language texts / K. Anton, G. Andrey // Proceedings of the Institute for System Programming of the Russian Academy of Sciences. - 2012. - Vol. 23. – P. 215-244.

Formation of multilayer knowledge graphs based on thematic texts modeling / Pimeshkov V. K. [et al.] // Transactions of the Kola Science Centre of RAS. Series: Engineering Sciences. 2024. Vol. 15, No. 3. P. 50–60.

A topic modeling‐based bibliometric exploration of automatic summarization research / X. Chen [et al.] // Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. – 2024. – Т. 14. – № 5. – P. e1540.

Bagul D.V. A novel content-based recommendation approach based on LDA topic modeling for literature recommendation / D.V. Bagul, S. Barve // 2021 6th International Conference on Inventive Computation Technologies (ICICT) 2021 6th International Conference on Inventive Computation Technologies (ICICT). – 2021. – P. 954-961.

Bansal S. Topic Modeling Driven Content Based Jobs Recommendation Engine for Recruitment Industry: 5th International Conference on Information Technology and Quantitative Management, ITQM 2017 / S. Bansal, A. Srivastava, A. Arora // Procedia Computer Science. – 2017. – Т. 122. – P. 865-872.

Benites-Lazaro L.L. Topic modeling method for analyzing social actor discourses on climate change, energy and food security: Special Issue on the Problems of Methods in Climate and Energy Research / L.L. Benites-Lazaro, L. Giatti, A. Giarolla // Energy Research & Social Science. – 2018. – Т. 45. – С. 318-330.

Blei D.M. Dynamic topic models / D.M. Blei, J.D. Lafferty // Proceedings of the 23rd international conference on Machine learning: ICML ’06. – New York, NY, USA: Association for Computing Machinery, 2006. – P. 113-120.

Blei D.M. Latent Dirichlet allocation / D.M. Blei, A.Y. Ng, M.I. Jordan // Journal of machine Learning research. – 2003. – Т. 3. – P. 993-1022.

Brewka G. Equilibria in heterogeneous nonmonotonic multi-context systems / G. Brewka, T. Eiter // Proceedings of the 22nd national conference on Artificial intelligence - Volume 1: AAAI’07. – Vancouver, British Columbia, Canada: AAAI Press, 2007. – P. 385-390.

Chang E. The use of SNOMED CT, 2013-2020: a literature review / E. Chang, J. Mostafa // Journal of the American Medical Informatics Association: JAMIA. – 2021. – Т. 28. – The use of SNOMED CT, 2013-2020. – № 9. – P. 2017-2026.

Dao-Tran M. Streaming Multi-Context Systems / M. Dao-Tran, T. Eiter // Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence. – 2017. – P. 1000-1007.

Davis E. Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problems / E. Davis, S. Aaronson arXiv:2308.05713 [cs]. – arXiv, 2025.

Garrido-Merchán E.C. GOFAI meets Generative AI: Development of Expert Systems by means of Large Language Models. GOFAI meets Generative AI / E.C. Garrido-Merchán, C. Puente arXiv:2507.13550 [cs]. – arXiv, 2025.

Grootendorst M. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. BERTopic / M. Grootendorst arXiv:2203.05794 [cs]. – arXiv, 2022.

Grover A. node2vec: Scalable Feature Learning for Networks. node2vec / A. Grover, J. Leskovec arXiv:1607.00653 [cs]. – arXiv, 2016.

Hybrid toxicology expert system: architecture and implementation of a multi-domain hybrid expert system for toxicology / G. Gini [et al.] // Chemometrics and Intelligent Laboratory Systems. – 1998. – Т. 43. – Hybrid toxicology expert system. – № 1. – P. 135-145.

Kommineni V.K. From human experts to machines: An LLM supported approach to ontology and knowledge graph construction. From human experts to machines / V.K. Kommineni, B. König-Ries, S. Samuel arXiv:2403.08345 [cs]. – arXiv, 2024.

Landauer T.K. An introduction to latent semantic analysis: Discourse Processes / Landauer T.K., Foltz P.W., Laham D. – 1998. – Т. 25. – № 2-3. – P. 259-284.

LLM-assisted Knowledge Graph Engineering: Experiments with ChatGPT / L.-P. Meyer [et al.] // arXiv:2307.06917 [cs]. – 2024. – LLM-assisted Knowledge Graph Engineering. – P. 103-115.

Managed Multi-Context Systems. / G. Brewka [et al.] journalAbbreviation: IJCAI International Joint Conference on Artificial Intelligence. – 2011. – 786 p.

MDFEND: Multi-domain Fake News Detection / Q. Nan [et al.] // Proceedings of the 30th ACM International Conference on Information & Knowledge Management / arXiv:2201.00987 [cs]. – 2021. – MDFEND. – P. 3343-3347.

Online multiscale dynamic topic models / T. Iwata [et al.] // Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining: KDD ’10. – New York, NY, USA: Association for Computing Machinery, 2010. – P. 663-672.

Ontology summit 2020 communiqué: Knowledge graphs / K. Baclawski [et al.] // Applied Ontology. – 2021. – Т. 16. – Ontology summit 2020 communiqué. – № 2. – P. 229-247.

Poo D. Multi‐domain expert systems / D. Poo, H. Lu // Expert Systems. – 2007. – Т. 8. – P. 67-73.

Public discourse and sentiment during the COVID 19 pandemic: Using Latent Dirichlet Allocation for topic modeling on Twitter / Jia Xue [et al.]. – 2020. – Т. 15. – № 9. – P. e0239441.

Reactive multi-context systems: Heterogeneous reasoning in dynamic environments / G. Brewka [et al.] // Artificial Intelligence. – 2018. – Т. 256. – Reactive multi-context systems. – P. 68-104.

The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty / L.D. Erman [et al.] // ACM Comput. Surv. – 1980. – Т. 12. – The Hearsay-II Speech-Understanding System. – № 2. – P. 213-253.

TopicGPT: A Prompt-based Topic Modeling Framework. TopicGPT / C.M. Pham [et al.] arXiv:2311.01449 [cs]. – arXiv, 2024.

Towards leveraging LLMs for Conditional QA / S.-A. Hussain [et al.] arXiv:2312.01143 [cs]. – arXiv, 2023.

Wilson A. Tracking topic birth and death in LDA / A. Wilson, D. Robinson. – 2011.

Belwal R.C. Extractive text summarization using clustering-based topic modeling / R.C. Belwal, S. Rai, A. Gupta // Soft Computing. – 2023. – Vol. 27. – № 7. – P. 3965-3982.

Bikakis A. Alternative Strategies for Conflict Resolution in Multi-Context Systems / A. Bikakis, G. Antoniou, P. Hassapis // Artificial Intelligence Applications and Innovations III / eds. Iliadis [et al.]. – Boston, MA: Springer US, 2009. – P. 31-40.

From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems / S. Janatian [et al.] // Legal Knowledge and Information Systems. – IOS Press, 2023. – From Text to Structure. – P. 167-176.

Gonçalves R. Evolving Bridge Rules in Evolving Multi-Context Systems / R. Gonçalves, M. Knorr, J. Leite // Computational Logic in Multi-Agent Systems / eds. N. Bulling [et al.]. – Cham: Springer International Publishing, 2014. – P. 52-69.

Know, Know Where, Knowwheregraph: A Densely Connected, Cross-Domain Knowledge Graph and Geo-Enrichment Service Stack for Applications in Environmental Intelligence / K. Janowicz [et al.] // AI Magazine. – 2022. – Vol. 43. – Know, Know Where, Knowwheregraph. – № 1. – P. 30-39.

Le T. Multi-context Systems with Preferences / T. Le, T.C. Son, E. Pontelli // PRIMA 2015: Principles and Practice of Multi-Agent Systems / eds. Q. Chen [et al.]. – Cham: Springer International Publishing, 2015. – P. 449-466.

Smywiński-Pohl A. Classifying the Wikipedia articles into the OpenCyc taxonomy / A. Smywiński-Pohl. – 2012.

UniProt Consortium. UniProt: the Universal Protein Knowledgebase in 2023 / UniProt Consortium // Nucleic Acids Research. – 2023. – Т. 51. – UniProt. – № D1. – P. D523-D531.

Yi X. A Comparative Study of Utilizing Topic Models for Information Retrieval / X. Yi, J. Allan // Advances in Information Retrieval / eds. M. Boughanem [et al.]. – Berlin, Heidelberg: Springer, 2009. – P. 29-41.