Machine Learning Analysis Advancing Security Planning

1Institute of ICT, Bulgarian Academy of Sciences, Acad. Georgi Bonchev Str., Bl. 25A, Sofia, 1113, Bulgaria
2Institute of Mathematics & Informatics, Bulgarian Academy of Sciences, Acad. Georgi Bonchev Str., Bl. 8, Sofia, 1113, Bulgaria
yulian.hristov@iict.bas.bg
zlatogor.minchev@gmail.com
DOI: 10.46793/BISEC25.098H

 

ABSTRACT: The rapid advancement of Artificial Intelligence and Large Language Models (LLMs) presents new opportunities for analyzing large-scale unstructured textual data, such as national security strategies. However, effective, machine-assisted methodologies for the qualitative analysis of such documents still remain under-developed. This study proposes opportunities for application of a hybrid method-ology that integrates computational text analysis with the sociological-linguistic framework of “graphing the graphs” by John W. Mohr and the dramatistic pentad of “grammar of motives” by Kenneth Burke. Applying natural language pro-cessing (NLP) techniques, including: named entity recognition (NER), sentiment analysis via specialized dictionaries, and contextual relationship extraction using tools like Voyant Tools – the framework enables the machine-assisted identifica-tion of key Actors, Actions, and Scenes within strategic texts. Experimentally ap-plied to three Bulgarian national security documents (1998–2018), the approach demonstrates the extraction of dominant terminology, key actors (Bulgaria, NATO, EU), and their contextual relationships. The results validate the potential of AI to support strategic analysis while highlighting limitations such as model hallucinations and data sensitivity risks. The proposed setup explicitly calls for further integration of machine learning, including advanced models for relation extraction and hybrid validation systems, aiming to increase automation, accura-cy, and scalability in the analysis of strategic narratives.

 

KEYWORDS: Security Planning, NLP, Machine Learning, Holistic System Modelling, Smart Security Analysis, Digital Humanities.

ACKNOWLEDGMENT: The authors of this study are granting special appreciations for the experimental base and partial funding support to the National Scientific Programme “Security & De-fense”. The analytical results presented in the paper are benefiting the international expert support obtained in the framework of the initiative “Securing Digital Future 21” with more than sixty countries now, spread around the world, https://securedfuture21.org/.

REFERENCES:

  1. Burke, A Grammar of Motives. Berkeley, CA, USA, Univ. of California Press, 1st edn, (1969)
  2. Moretti, Graphs, Maps, Trees: Abstract Models for Literary History. London, UK: Ver-so, 1st edn, (2005)
  3. Natural Language Toolkit, version 3.9.1. (2025), https://www.nltk.org/, last accessed 2026/02/11
  4. spaCy: Industrial-Strength Natural Language Processing in Python. Explosion, https://spacy.io/, last accessed 2026/02/11
  5. Levinson, How to Keep Generative AI from Crashing in Combat, War on the Rocks, (2025), https://shorturl.at/HeS5U, last accessed 2026/02/11
  6. The White House, Winning the Race: America’s AI Action Plan, (2025), https://whitehouse.gov/wp-content/uploads/2025/07/Americas-AI-Action-Plan.pdf, last ac-cessed 2026/02/11
  7. Hunter, B. Bowen, We’ll never have a model of an AI major-general: Artificial Intelli-gence, command decisions, and kitsch visions of war, Journal of Strategic Studies, (2023), https://doi.org/10.1080/01402390.2023.224164, last accessed 2026/02/11
  8. J.-P. Rivera, G. Mukobi, A. Reuel, M. Lamparth, Ch. Smith, and J. Schneider, Escalation risks from language models in military and diplomatic decision-making, in Proc.         2024 ACM Conf. Fairness, Accountability, and Transparency      (FAccT), 836–898, (2024), https://dl.acm.org/doi/10.1145/3630106.3658942, last accessed 2026/02/11
  9. W. Mohr, R. Wagner-Pacifici, R. L. Breiger, and P. Bogdanov, Graphing the grammar of motives in National Security Strategies: Cultural interpretation, automated text analysis and the drama of global politics, Poetics, vol. 41, no. 6, 670–700, (2013), https://doi.org/10.1016/j.poetic.2013.08.003, last accessed 2026/02/11
  10. Shopov and S. Gerdjikov, Consistent Bidirectional Language Modelling: Expressive Power and Representational Conciseness, in Proc. 2024 Conf. Empirical Methods in Natural Language Processing (EMNLP), 5724 –5768, (2024), https://aclanthology.org/2024.emnlp-main.328/, last accessed 2026/02/11
  11. Liu, Z. Yu, Y. Zhang, N. Zhang, and C. Xiao, Automatic and Universal Prompt Injection Attacks against Large Language Models, (2024), https://arxiv.org/abs/2403.04957, last ac-cessed 2026/02/11
  12. Sinclair, and G. Rockwell, Voyant Tools, (2016), voyant-tools.org, last accessed 2026/02/11
  13. Jensen, I. Reynolds, Y. Atalan, Critical Foreign Policy Decisions (CFPD)-Benchmark: Measuring Diplomatic Preferences in Large Language Models, Center for Strategic and In-ternational Studies, Washington, DC, USA, https://arxiv.org/html/2503.06263v1, last ac-cessed 2026/02/11
  14. N. Caballero and P. R. Jenkins, On large language models in national security applica-tions, Stat, vol. 14, no. 2, p. e70057, (2025), https://doi.org/10.1002/sta4.70057, last ac-cessed 2026/02/11
  15. Chawla, N. Mulay, V. Bishnoi, and G. Dhama, KARL-Trans-NER: Knowledge Aware Representation Learning for Named Entity Recognition using Transformers, (2021), https://arxiv.org/abs/2111.15436, last accessed 2026/02/11
  16. Antony, and G. Mahalakshmi, Content-based Information Retrieval by Named Entity Recognition and Verb Semantic Role Labelling, J. Universal Comput. Sci., vol. 21, no. 13, 1830–1848, https://www.jucs.org/jucs_21_13/content_based_information_retrieval.html, last accessed 2026/02/11
  17. Mishra, Information Professionals and Big Data, Int. J. Adv. Res. Comput. Sci. Softw. Eng., vol. 5, no. 9, 317 – 321, https://www.ijarcsse.com/docs/papers/Volume_5/9_September2015/V5I9-0214.pdf, last ac-cessed 2026/02/11
  18. Papadopoulos, and Y. Charalabidis, What do governments plan in the field of artificial in-telligence?: Analysing national AI strategies using NLP, in Proc. 13th Int. Conf. Theory Pract. Electron. Governance (ICEGOV), 100–111, (2020) https://doi.org/10.1145/3428502.3428514, last accessed 2026/02/11, last accessed 2026/02/11
  19. Blei, A. Ng, and M. Jordan, Latent Dirichlet Allocation, J. Mach. Learn. Res., vol. 3, 993–1022, (2003), https://dl.acm.org/doi/10.5555/944919.944937, last accessed 2026/02/11

 

IZVOR: Proceedings of the 16th International Conference on Business Information Security BISEC’2025