Victoria Vysotska; Lyubomyr Chyrun; Oleksandr Lavrut; Zhengbing Hu; Yurii Ushenko

Hybrid Information Technology for Automatic Detection of Disinformation and Inauthentic Behaviour of Chat Users based on NLP, Machine Learning, and Graph Analysis

PDF (3352KB), PP.180-245

Views: 0 Downloads: 0

Author(s)

Victoria Vysotska ^1,2 Lyubomyr Chyrun ^1,3 Oleksandr Lavrut ⁴ Zhengbing Hu ⁵ Yurii Ushenko ^6,7

1. Information Systems and Networks Department, Lviv Polytechnic National University, Lviv, 79013, Ukraine

2. Combating Cybercrime Department, Kharkiv National University of Internal Affairs, Kharkiv, 61080, Ukraine

3. Department of Applied Mathematics Department, Ivan Franko National University of Lviv, Lviv, 79000, Ukraine

4. Tactics Department, Hetman Petro Sahaidachnyi National Army Academy, Lviv, 79012, Ukraine

5. School of Computer Science and Artificial Intelligence, Hubei University of Technology, Wuhan, China

6. Department of Physics, Shaoxing University, Shaoxing, Zhejiang Province 312000, China

7. Department of Computer Science, Yuriy Fedkovych Chernivtsi National University, Chernivtsi, 58012, Ukraine

* Corresponding author.

DOI: https://doi.org/10.5815/ijitcs.2026.01.10

Received: 11 Jul. 2025 / Revised: 15 Sep. 2025 / Accepted: 24 Oct. 2025 / Published: 8 Feb. 2026

Index Terms

Disinformation, Fake News, Information Security, Inauthentic Behaviour, Bots, Social Media, Natural Language Processing, Machine Learning, Graph Analysis, Cybersecurity

Abstract

In the context of the growth of information exchange in social networks, messengers, and chats, the problem of spreading disinformation and coordinated inauthentic behaviour by users is becoming increasingly relevant and poses a threat to the state's information security. Traditional manual monitoring methods are ineffective due to the scale and speed of information dissemination, necessitating the development of intelligent automated countermeasures. The paper proposes a hybrid information technology for the automatic detection of disinformation, its sources of spread, and inauthentic behaviour among chat users, combining methods of natural language processing (NLP), machine learning, stylistic and linguistic analysis of texts, and graph analysis of social interactions. Within the study, datasets of authentic and fake messages were compiled, and mathematical models and algorithms for identifying disinformation sources were developed using metrics of graph centrality, clustering, and bigram Laplace smoothing.
Experimental studies using TF-IDF, BERT, MiniLM, ensemble methods, and transformers confirmed the effectiveness of the proposed approach. The achieved accuracy in disinformation classification is up to 89.5%, and integrating content, network, and behavioural analysis significantly improves the quality of detecting coordinated information attacks. The results obtained are both scientifically novel and of practical value. They can be used to create systems for monitoring information threats, supporting cybersecurity decision-making, fact-checking, and protecting Ukraine's information space.

Cite This Paper

Victoria Vysotska, Lyubomyr Chyrun, Oleksandr Lavrut Zhengbing Hu, Yurii Ushenko, "Hybrid Information Technology for Automatic Detection of Disinformation and Inauthentic Behaviour of Chat Users based on NLP, Machine Learning, and Graph Analysis", International Journal of Information Technology and Computer Science(IJITCS), Vol.18, No.1, pp.180-245, 2026. DOI:10.5815/ijitcs.2026.01.10

Reference

[1]P. Dhanasekaran, H. Srinivasan, S. S. Sree, I. S. G. Devi, S. Sankar, and V. Vijayaraghavan, “SOMPS-Net: Attention-based social graph framework for early detection of fake health news,” in Australasian Conference on Data Mining, Singapore: Springer, pp. 165–179, 2021.
[2]M. Mayank, S. Sharma, and R. Sharma, “DEAP-FAKED: Knowledge graph based approach for fake news detection,” in 2022 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 47–51, 2022.
[3]F. B. Mahmud, M. M. S. Rayhan, M. H. Shuvo, I. Sadia, and M. K. Morol, “A comparative analysis of graph neural networks and commonly used machine learning algorithms on fake news detection,” in 2022 7th International Conference on Data Science and Machine Learning Applications (CDMA), pp. 97–102, 2022.
[4]A. Kar, S. S. Chamarthy, K. K. Tirupati, S. Kumar, M. Prasad, and P. Vashishtha, “Social media misinformation detection: NLP approaches for risk,” Journal of Quantum Science and Technology, vol. 1, no. 4, pp. 88–124, 2024.
[5]Y. Shen, Q. Liu, N. Guo, J. Yuan, and Y. Yang, “Fake news detection on social networks: A survey,” Applied Sciences, vol. 13, no. 21, Art. no. 11877, 2023.
[6]V. Indu and S. M. Thampi, “Misinformation detection in social networks using emotion analysis and user behavior analysis,” Pattern Recognition Letters, vol. 182, pp. 60–66, 2024.
[7]R. K. Ayyasamy, C. Ponnusamy, K. N. Bhargavi et al., “A hybrid deep learning framework for fake news detection using LSTM-CGPNN and metaheuristic optimization,” Scientific Reports, vol. 15, Art. no. 41522, 2025.
[8]M. E. Almandouh, M. F. Alrahmawy, M. Eisa et al., “Ensemble-based high performance deep learning models for fake news detection,” Scientific Reports, vol. 14, Art. no. 26591, 2024.
[9]S. Munir and H. Munir, “NLP-based approach to multilingual fake news detection through social media in low-resource languages,” Preprints, 2025.
[10]V. Vysotska, S. Popp, V. Bulatova, Z. Hu, Y. Ushenko, and D. Uhryn, “Smart tool for identifying misinformation spread sources and routes in social networks based on NLP and machine learning,” International Journal of Computer Network and Information Security, vol. 17, no. 5, pp. 114–165, 2025.
[11]M. Nyzova, V. Vysotska, L. Chyrun, Z. Hu, Y. Ushenko, and D. Uhryn, “Smart tool for text content analysis to identify key propaganda narratives and disinformation in news based on NLP and machine learning,” International Journal of Computer Network and Information Security, vol. 17, no. 4, pp. 113–175, 2025.
[12]R. Lynnyk, V. Vysotska, Z. Hu, D. Uhryn, L. Diachenko, and K. Smelyakov, “Information technology for modelling social trends in Telegram using E5 vectors and hybrid cluster analysis,” International Journal of Information Technology and Computer Science, vol. 17, no. 4, pp. 80–119, 2025.
[13]K. I. Roumeliotis, N. D. Tselikas, and D. K. Nasiopoulos, “Fake news detection and classification: A comparative study of convolutional neural networks, large language models, and natural language processing models,” Future Internet, vol. 17, no. 1, 2025.
[14]L. Ji and H. Xie, “A modified method on improving power grid resilience based on the Louvain algorithm,” Sustainable Energy, Grids and Networks, Art. no. 101883, 2025.
[15]S. H. H. Anuar, Z. A. Abas, N. M. Yunos, N. H. M. Zaki, N. A. Hashim, and M. F. Mokhtar, “Comparison between Louvain and Leiden algorithm for network structure: A review,” Journal of Physics: Conference Series, vol. 2129, no. 1, Art. no. 012028, 2021.
[16]V. A. Traag, L. Waltman, and N. J. van Eck, “From Louvain to Leiden: guaranteeing well-connected communities,” Scientific Reports, vol. 9, no. 1, pp. 1–12, 2019.
[17]N. Singlan, F. Abou Choucha, and C. Pasquier, “A new similarity based adapted Louvain algorithm (SIMBA) for active module identification in p-value attributed biological networks,” Scientific Reports, vol. 15, no. 1, Art. no. 11360, 2025.
[18]B. Sharma, P. Kathirvel, and S. R. Hegde, “Identifying communities in the virus–host protein–protein interaction networks,” in Computational Virology, New York, NY, USA: Springer, pp. 307–319, 2025.
[19]V. D. Blondel, J.-L. Guillaume, R. Lambiotte, and E. Lefebvre, “Fast unfolding of communities in large networks,” Journal of Statistical Mechanics: Theory and Experiment, no. 10, Art. no. P10008, 2008.
[20]R. Hernández, I. Gutiérrez, and J. Castro, “Social network analysis: A novel paradigm for improving community detection,” International Journal of Computational Intelligence Systems, vol. 18, no. 1, p. 87, 2025.
[21]D. H. Do and T. H. D. Phan, “An improvement on the Louvain algorithm using random walks,” Journal of Combinatorial Optimization, vol. 50, no. 2, Art. no. 14, 2025.
[22]Vysotska, V., Hu, Z., Mykytyn, N., Nagachevska, O., Hazdiuk, K., & Uhryn, D. (2025). Development and Testing of Voice User Interfaces Based on BERT Models for Speech Recognition in Distance Learning and Smart Home Systems. International Journal of Computer Network and Information Security (IJCNIS), 17(3), 109-143.
[23]Vysotska, V., Przystupa, K., Kulikov, Y., Chyrun, S., Ushenko, Y., Hu, Z., & Uhryn, D. (2025). Recognizing Fakes, Propaganda and Disinformation in Ukrainian Content based on NLP and Machine-learning Technology. International Journal of Computer Network and Information Security, 17(1), 92-127.
[24]Vysotska, V., Yatsyshyn, M., Romanchuk, R., & Danylyk, V. (2025). Information technology for automatic detection of calls for terrorist acts in social media posts and comments based on machine learning. CEUR Workshop Proceedings, Vol-4126, 2025, 306-360, https://ceur-ws.org/Vol-4126/paper18.pdf
[25]Motyka, V., Vysotska, V., Chyrun, L., Markiv, O., Chyrun, S., & Kolyasa, L. (2023, October). System Project for Ukrainian-language Feedback Tonality Analysis in the Health Care Field Based on BERT Model. In 2023 IEEE 18th International Conference on Computer Science and Information Technologies (CSIT) (pp. 1-6). IEEE.
[26]Victoria Vysotska, Denys Ptushkin, Rostyslav Fedchuk, Roman Lynnyk, Probabilistic thematic modelling of Ukrainian-language texts based on the Latent Dirichlet Allocation algorithm. CEUR Workshop Proceedings, Vol-4126, 2025, 226-291, https://ceur-ws.org/Vol-4126/paper16.pdf
[27]N. Khairova, Y. Holyk, D. Sytnikov, Y. Mishcheriakov, N. Shanidze, (2024). Topic modelling of Ukraine war-related news using Latent Dirichlet Allocation with collapsed Gibbs sampling. In 8th International Conference on Computational Linguistics and Intelligent Systems, Lviv, Ukraine, April 12-13, 2024 (pp. 1-15). CEUR-WS.
[28]V. Vysotska, N. Babkova, D. Huliieva, Z. Kochuieva, N. Ugolnikova, M. Kozulia, Identifying fake news in political discourse behavior using machine learning methods, CEUR Workshop Proceedings, Vol-4015, 2025, 163-174, https://ceur-ws.org/Vol-4015/paper12.pdf
[29]V. Vysotska, M. Nazarkevych, D. Shamota, Information Technology for Referencing Ukrainian-Language News at Detecting Disinformation in Cybersecurity, CEUR Workshop Proceedings, Vol-4150, 2025, 81-95, https://ceur-ws.org/Vol-4150/paper8.pdf
[30]V., Vysotska, A., Chupryna, N., Valenda, O. Konduforov, Evaluating the in-context learning capabilities of large language models for misinformation detection for Ukrainian news. CEUR Workshop Proceedings, Vol-4110, 2025, 181-197, https://ceur-ws.org/Vol-4110/paper15.pdf
[31]Pankratz, B., Kamiński, B., & Prałat, P. (2024). Performance of community detection algorithms supported by node embeddings. Journal of Complex Networks, 12(4), cnae035.
[32]Melhem, A., Halloush, Z., & Aleroud, A. (2024, October). Dynamic Network Analysis of Cognitive Attacks Using Meta-Network Modeling and Community Detection Algorithms. In 2024 IEEE 6th International Conference on Cognitive Machine Intelligence (CogMI) (pp. 240-246). IEEE.
[33]Yang, J., Vega-Oliveros, D., Seibt, T., & Rocha, A. (2021, December). Scalable fact-checking with human-in-the-loop. In 2021 IEEE International Workshop on Information Forensics and Security (WIFS) (pp. 1-6). IEEE.
[34]Zheng, Q., Zeng, L., & Gu, Z. (2025, October). From IPs to Threat Groups: Community Detection on Rule-Enhanced Homology Graphs. In International Conference on Advanced Data Mining and Applications (pp. 316-324). Singapore: Springer Nature Singapore.
[35]Alrasheed, H. (2021). Word synonym relationships for text analysis: A graph-based approach. Plos one, 16(7), e0255127.
[36]Tokala, S., Enduri, M. K., Lakshm, T. J., & Hajarathaiah, K. (2025). Evaluating Community Detection Algorithms: A Focus on Effectiveness and Efficiency. Journal of Scientometric Research, 14(1), 62-74.

International Journal of Information Technology and Computer Science (IJITCS)