International Journal of Computer Network and Information Security (IJCNIS)
IJCNIS Vol. 17, No. 4, 8 Aug. 2025
Cover page and Table of Contents: PDF (size: 962KB)
Identifying Influential Nodes in the Spread of Criminal Information in Social Networks
PDF (962KB), PP.84-99
Views: 0 Downloads: 0
Author(s)
Shynar Mussiraliyeva
1
Gulshat Baispay
1,*
Ihor Tereikovskyi
2
Index Terms
Information Security, Crime, Social Networks, Social Network Analysis (SNA), Influence Detection, Centrality Measures, Criminal Information Dissemination, Cybercrime
Abstract
The purpose of this work is to develop an algorithm and a method for identifying key nodes involved in the dissemination of criminal information within social networks. This study focuses on social network analysis (SNA) metrics that facilitate the detection of influential actors in organized groups, particularly activists who serve as primary disseminators of criminal content. The research objects include both the textual content and metadata of users on social media platforms such as "Vkontakte" and "YouTube." To achieve this goal, an algorithm for detecting nodes that distribute criminal information has been developed. A conceptual model has been constructed, integrating network analysis principles with computational techniques to assess influence. This model introduces a novel framework for evaluating social network nodes based on a combination of structural, semantic, and emotional factors. Specifically, it incorporates influence assessment metrics that consider the heterogeneous nature of content, including its linguistic features, sentiment, and patterns of engagement. Additionally, the model accounts for the emission dynamics of criminal content, allowing for a more precise determination of high-risk nodes within the network. A method for quantifying the influence of social network nodes engaged in criminal content dissemination has been formulated. This method utilizes centrality measures along with content analysis techniques to improve accuracy in detecting key actors. Experimental validation conducted on multiple real-world datasets (including VKontakte groups and known extremist networks) demonstrated that the proposed method achieves an accuracy of up to 80% in identifying the most influential criminal nodes. Compared to baseline centrality-based methods, our approach provides more reliable detection due to the integration of semantic-emotional metrics and emission indicators. The results confirm the practical value of the method in operational scenarios such as the early detection of criminal activity and the prioritization of threat actors for monitoring. These findings have strong implications for real-world applications in law enforcement and cybersecurity. By leveraging advanced algorithmic techniques for social network monitoring, authorities can proactively detect and mitigate the spread of criminal information.
Cite This Paper
Shynar Mussiraliyeva, Gulshat Baispay, Ihor Tereikovskyi, "Identifying Influential Nodes in the Spread of Criminal Information in Social Networks", International Journal of Computer Network and Information Security(IJCNIS), Vol.17, No.4, pp.84-99, 2025. DOI:10.5815/ijcnis.2025.04.05
Reference
[1]Wan Z, Mahajan Y, Kang BW, Moore TJ, Cho JH. A survey on centrality metrics and their network resilience analysis. IEEE Access. 2021;9:104773–104819. doi:10.1109/ACCESS.2021.3094196.
[2]Kumar P, Sinha A. Information diffusion modeling and analysis for socially interacting networks. Soc Netw Anal Min. 2021;11(1):1–18. doi:10.1007/s13278-020-00719-7.
[3]Shahid W, Li Y, Staples D, Amin G, Hakak S, Ghorbani A. Are you a cyborg, bot or human? A survey on detecting fake news spreaders. IEEE Access. 2022;10:27069–27083. doi:10.1109/ACCESS.2022.3157724.
[4]Sonjaya S, Yudapratama A, Aji AP, Muhardi I, Simbolon WB. Law enforcement against the spread of fake news on social media in relation to Law Number 19 of 2016 concerning information and electronic transactions. Hist Med. 2023;9(1):1297–1307. doi:10.33258/polit.v2i1.627.
[5]Di Domenico G, Nunan D, Pitardi V. Marketplaces of misinformation: A study of how vaccine misinformation is legitimized on social media. J Public Policy Mark. 2022;41(4):319–335. doi:10.1177/07439156221103860.
[6]Sudha R, Maheswari NU, Venkatesh R. A survey and analysis on online social networks. J Algebraic Stat. 2022;13(2):1414–1420. doi:10.52783/jas.v13i2.303.
[7]Chicago-crime dataset. [Internet]. 2017 [cited 2024 Sep 10]. Available from: https://www.kaggle.com/datasets/chicago/chicago-crime.
[8]Bogomolov A, Lepri B, Staiano J, Oliver N, Pianesi F, Pentland A. Once upon a crime: Towards crime prediction from demographics and mobile data. Proceedings of the 16th ACM International Conference on Multimodal Interaction (ICMI); 2014:427–434. doi:10.1145/2663204.2663254.
[9]Wang T, Rudin C, Wagner D, Sevieri R. Detecting patterns of crime with series finder. Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2013:140–142.
[10]Gerber MS. Predicting crime using Twitter and kernel density estimation. Decis Support Syst. 2014;61:115–125. doi:10.1016/j.dss.2014.02.003.
[11]New York City Crime Data. [Internet]. 2015 [cited 2024 Sep 10]. Available from: https://www.kaggle.com/datasets/adamschroeder/crimes-new-york-city.
[12]San Francisco Police Department Incident Reports. [Internet]. [cited 2024 Sep 10]. Available from: https://www.kaggle.com/code/serkanp/san-francisco-crime-analysis-data-visualization.
[13]Taha K, Yoo PD. Shortlisting the influential members of criminal organizations and identifying their important communication channels. IEEE Trans Inf Forensics Secur. 2019;14(8):1988–1999. doi:10.1109/TIFS.2018.2890811.
[14]Kirichenko L, Radivilova T, Carlsson A. Detecting cyber threats through social network analysis: short survey. SocioEcon Chall. 2017;1:20–34. doi:10.21272/sec.2017.1-03.
[15]Nouh M, Nurse J. Identifying key players in online activist groups on Facebook social network. IEEE Comput Soc. 2015;969–978. doi:10.1109/ICDMW.2015.88.
[16]Garcia L, Rodriguez S. Centrality measures in network analysis: A comparative review. J Netw Sci. 2020;35(3):256–278. doi:10.1051/e3sconf/202339908002.
[17]Hansen DL, Shneiderman B, Smith MA, Himelboim I. Social network analysis: measuring, mapping, and modeling collections of connections. Analyzing Social Media Networks with NodeXL. 2020;31–51. doi:10.1016/b978-0-12-817756-3.00003-0.
[18]Wei X, Zhao J, Liu S, Wang Y. Identifying influential spreaders in complex networks for disease spread and control. Sci Rep. 2022;12. doi:10.1038/s41598-022-09341-3.
[19]Open Data Portal of the Moscow Government. [Internet]. [cited 2024 Sep 10]. Available from: https://data.mos.ru/.
[20]EurAsia Daily. "The number of people convicted of terrorism and extremism is growing in Kazakhstan." [Internet]. [cited 2024 Sep 10]. Available from: http://eadaily.com:8080/ru/news/2019/11/19/vkazahstane-rastet-chislo-osuzhdennyh-za-terrorizm-i-ekstremizm.
[21]Central Asian Bureau for Analytical Reporting. "Will Kazakhstan take a new approach to fighting extremists?" [Internet]. [cited 2024 Sep 10]. Available from: https://cabar.asia/ru/kazahstan-stanetpo-novomu-borotsya-s-ekstremistami/.
[22]Krebs’s 9/11 dataset. [Internet]. [cited 2022 Dec 12]. Available from: https://sites.google.com/site/ucinetsoftware/datasets/covert-networks/911hijackers.
[23]Caviar dataset. [Internet]. [cited 2022 Dec 12]. Available from: https://sites.google.com/site/ucinetsoftware/datasets/covert-networks/caviar.
[24]How ISIS Uses Twitter dataset. [Internet]. [cited 2022 Dec 12]. Available from: https://www.kaggle.com/fifthtribe/how-isisuses-twitter.
[25]Ficara A, Fiumara G, Catanese S, De Meo P, Liu X. The whole is greater than the sum of the parts: A multilayer approach on criminal networks. Future Internet. 2022;14(5):123. doi:10.3390/fi14050123.
[26]Kumar G, Singh JP, Singh AK. Autoencoder-based feature extraction for identifying hate speech spreaders in social media. IEEE Trans Comput Soc Syst. 2023. doi:10.1109/TCSS.2023.3240098.
[27]Riquelme F, Vera JA. A parameterizable influence spread-based centrality measure for influential user detection in social networks. Knowl Based Syst. 2022; 257:109922. doi: 10.1016/j.knosys.2022.109922.
[28]Ahvanooey MT, Zhu MX, Mazurczyk W, Choo KKR, Conti M, Zhang J. Misinformation detection on social media: Challenges and the road ahead. IT Prof. 2022;24(1):34–40. doi:10.1109/MITP.2021.3120876.
[29]Mussiraliyeva S, Baispay G. Leveraging machine learning methods for crime analysis in textual data. Int J Adv Comput Sci Appl (IJACSA). 2024;15(4). doi:10.14569/IJACSA.2024.0150424.
[30]Zhenisbekovna MS, Aslanbekkyzy BM, Bolatkyzy BG. Investigating long short-term memory approach for extremist messages detection in Kazakh language. Expert Syst. 2024;e13595. doi:10.1111/exsy.13595.
[31]Aidara NK, Diop IM, Diallo C, Cherifi H. Detecting influential nodes with centrality measures via random forest in social networks. IEEE Workshop on Complexity in Engineering (COMPENG); 2024:1–6. doi:10.1109/COMPENG60905.2024.10741428.
[32]Mussiraliyeva S, Baispay G, Ospanov R, Medetbek Z, Shalabayev K. Graphical visualization of the connections of involved users and identifying influential spreaders in a social network. 9th Int Conf on Electrical and Electronics Engineering (ICEEE); 2022:311–315. doi:10.1109/ICEEE55327.2022.9772556.
[33]Al-Hassan A, Al-Dossari H. Detection of hate speech in social networks using deep learning: A review. Int J Adv Comput Sci Appl. 2019;10(12). doi:10.14569/IJACSA.2019.0101212.
[34]Scrivens R, Gill P, Conway M. The role of artificial intelligence in online extremism research: A systematic review and future research agenda. Terror Polit Viol. 2020;32(4):742–776. doi:10.1080/09546553.2018.1505312.
[35]Jiashu Xu, Sergii Stirenko,"Self-Supervised Model Based on Masked Autoencoders Advance CT Scans Classification", International Journal of Image, Graphics and Signal Processing, Vol.14, No.5, pp. 1-9, 2022.