APPLICATION OF ARTIFICIAL INTELLIGENCE FOR AUTOMATED ASSESSMENT OF SITUATIONAL TASKS IN CYBERSECURITY TRAINING

DOI: 10.31673/2786-8362.2025.012293

Abstract

The
article considers the problem of objective assessment of students' success in performing situational tasks in
higher education institutions, in particular in conditions of distance and blended learning. Analysis of
scientific publications indicates the influence of the contrast effect during assessment and the risks of
subjectivity inherent in traditional assessment methods. An automated assessment tool is proposed, based
on semantic comparison of students' answers with a reference answer, using natural language processing
(NLP) technologies and a mathematically based sentence transformer model. Based on standard Python
libraries, an improved model for automatic assessment of text situational tasks has been developed, which
performs a comprehensive analysis of the semantic and lexical coherence and completeness of students'
answers in comparison with the reference answer. Modeling and testing demonstrated a high Pearson
correlation coefficient (>0.95) between the scores generated by the model and expert assessments, which
confirms the accuracy and reliability of the results. A key advantage of the model is its ability to detect
internal plagiarism in student responses, thus supporting academic integrity. The model also significantly
reduces the time required for grading compared to traditional approaches and allows for visualization of
potential similarities.
Keywords: information technology, artificial intelligence, situational learning, automatic assessment,
cybersecurity

References
1. Increasing Teacher Competence in Cybersecurity Using the EU Security Frameworks / I.
Ievgeniia Kuzminykh et al. International Journal of Modern Education and Computer Science. 2021.
Vol. 13, no. 6. P. 60–68. URL: https://doi.org/10.5815/ijmecs.2021.06.06.
2. Brandão A., Pedro L., Zagalo N. Teacher professional development for a future with
generative artificial intelligence – an integrative literature review. Digital Education Review. 2024.
No. 45. P. 151–157. URL: https://doi.org/10.1344/der.2024.45.151-157.
3. Gallego-Arrufat M.-J., Torres-Hernández N., Pessoa T. Competence of future teachers in the
digital security area. Comunicar. 2019. Vol. 27, no. 61. P. 57–67. URL: https://doi.org/10.3916/c61-
2019-05.
4. P.A.L. Nadeesha, T.A. Weerasinghe, W.R.N.S Abeyweera. Automatic scoring of knowledge
gained and shared through discussion forums: based on the community of inquiry model. Information
Technologies and Learning Tools. 2025. Vol. 105, no. 1. P. 85–102. URL:
https://doi.org/10.33407/itlt.v105i1.5912.
5. Application of artificial intelligence for improving situational training of cybersecurity
specialists / Y. V. Shchavinsky et al. Information Technologies and Learning Tools. 2023. Vol. 97,
no. 5. P. 215–226. URL: https://doi.org/10.33407/itlt.v97i5.5424.
6. Bi X., Shi X., Zhang Z. Cognitive machine learning model for network information safety.
Safety Science. 2019. Vol. 118. P. 435–441. URL: https://doi.org/10.1016/j.ssci.2019.05.032.
7. The Current Research Status of AI-Based Network Security Situational Awareness / M. Wang
et al. Electronics. 2023. Vol. 12, no. 10. P. 2309. URL: https://doi.org/10.3390/electronics12102309.
8. AI-Empowered Multimodal Hierarchical Graph-Based Learning for Situation Awareness on
Enhancing Disaster Responses / J. Chen et al. Future Internet. 2024. Vol. 16, no. 5. P. 161. URL:
https://doi.org/10.3390/fi16050161.
9. Burrows S., Gurevych I., Stein B. The Eras and Trends of Automatic Short Answer Grading.
International Journal of Artificial Intelligence in Education. 2014. Vol. 25, no. 1. P. 60–117. URL:
https://doi.org/10.1007/s40593-014-0026-8.
10. Progress in Neural NLP: Modeling, Learning, and Reasoning / M. Zhou et al. Engineering.
2020. Vol. 6, no. 3. P. 275–290. URL: https://doi.org/10.1016/j.eng.2019.12.014.
11. Reimers N., Gurevych I. Sentence-BERT: Sentence Embeddings using Siamese BERTNetworks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language
Processing and the 9th International Joint Conference on Natural Language Processing (EMNLPIJCNLP), Hong Kong, China. Stroudsburg, PA, USA, 2019. URL: https://doi.org/10.18653/v1/d19-
1410.