Architecture of a social media bot detection system
DOI:
https://doi.org/10.17721/1812-5409.2025/2.29Keywords:
bot, API, NLP, system architectureAbstract
Modern information systems require efficient architectures to ensure high performance, scalability, and reliability. This article presents an approach to system architecture design that incorporates the latest technological solutions and methods for optimizing the processing of large data sets. The paper proposes an original architecture of a bot detection system based on the microservices paradigm and modern data processing techniques. Unlike existing solutions, the proposed system does not aim to develop a radically new classification method but focuses on the effective integration of well-established approaches within a unified architecture.
The advancement of information technologies requires the development of architectural solutions that guarantee high performance and reliability of software systems. With the increasing volume of data and growing demands for processing speed, traditional architectural approaches require refinement. Research in this field is important for software developers and system architects.
The aim of this study is to develop an architectural concept that meets modern requirements for performance, scalability, and security. The main objectives include analyzing existing approaches, identifying their advantages and drawbacks, and designing an efficient architecture that minimizes resource consumption and increases data processing speed.
The study employed methods of architectural analysis, system modeling, performance testing, and comparative evaluation of different approaches. For the implementation of the architecture, modern technologies were used, including the microservices paradigm, containerization, and distributed computing.
The proposed architecture improves system performance by optimizing request processing and distributing workloads across services. The use of containerization and orchestration enables flexible scalability and enhances system stability. Performance analysis has shown reduced request processing latency and efficient utilization of server resources.
The developed architecture has proven its effectiveness in test environments and can be applied to high-load systems. Future research directions include the integration of artificial intelligence for automatic scaling and service optimization, as well as studying the impact of different caching strategies on overall system performance.
Pages of the article in the issue: 187 - 192
Language of the article: Ukrainian
References
Antispoofing Wiki. (2024). Detecting Bot-Generated Fake News in Social Media. Antispoofing Wiki. https://antispoofing.org/detecting-bot-generated-fake-news-in-social-media/
Dehghan, A., Siuta, K., Skorupka, A., Dubey, A., Betlen, A., Miller, D., Xu, W., Kamiński, B., & Prałat, P. (2023). Detecting bots in social-networks using node and structural embeddings. Journal of Big Data, 10(119). https://doi.org/10.1186/s40537-023-00796-3
Devle, A. C., Jose, J. A., Saraswathula, A. S., Mehta, S., Srivastava, S., Kona, S., & Daggumalli, S. (2021). BotNet detection on social media. arXiv. https://doi.org/10.48550/arXiv.2110.05661
Ellaky Z., Benabbou F., Matrane Y., & Qaqa S. (2024). A Hybrid Deep Learning Architecture for Social Media Bots Detection Based on Bigru-LSTM and Glove Word Embedding. IEEE Access, 12, 100278-100294. https://doi.org/10.1109/ACCESS.2024.3430859
Imperva. (2024). Bad Bot Report. Imperva. https://www.imperva.com/resources/resource-library/reports/2024-bad-bot-report/
Lin J. (2019). Deploying a scalable web application with Docker and Kubernetes. Medium. https://medium.com/better-practices/deploying-a-scalable-web-application-with-docker-and-kubernetes-a5000a06c4e9
Pote, M. (2024). Computational Propaganda Theory and Bot Detection System: Critical Literature Review. arXiv. https://doi.org/10.48550/arXiv.2404.05240
Sen, I., Aggarwal, A., Mian, S., & Singh, S. (2018). Worth its Weight in Likes: Towards Detecting Fake Likes on Instagram. In Proceedings of the 10th ACM Conference on Web Science, WebSci 2018: The Reality of Social Media (pp. 205–209). Association for Computing Machinery. http://dx.doi.org/10.1145/3201064.3201105
Statsig. (2024). Real-time data processing with Apache Kafka. Satsig. https://www.statsig.com/perspectives/real-time-data-processing-with-apache-kafka
Tzoumanekas, G., Chatzianastasis, M., Ilias, L., Kiokes, G., Psarras, J., & Askounis, D. (2024). A Graph Neural Architecture Search Approach for Identifying Bots in Social Media. Front. Artif. Intell. https://doi.org/10.48550/arXiv.2411.16285
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Mykhailo Makhno, Oleksii Fedorus, Oleksandr Borysenko, Maksym Veremchuk
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
