Abstract
The article examines how the use of artificial intelligence reshapes approaches to conducting comparative studies of political regime transformations. The relevance of the topic is associated with the shift from the traditional analysis of limited samples to the processing of large-scale datasets, which makes it possible to capture dynamic changes more accurately and on a broader empirical basis. The study aims to identify and assess how algorithmic tools influence the selection of indicators, measurement methods, and interpretation of results in comparative political science. The research combines qualitative case comparison, analysis of political indicator databases, and modeling based on machine learning algorithms. Particular attention is paid to the shift in research logic from explanatory to predictive models. At the same time, the changing role of the researcher under conditions of increasing reliance on digital tools is analyzed. The findings show that the use of intelligent systems makes it possible in practice to automate data collection and processing, reduce subjectivity in regime classification, and identify hidden patterns in their transformation. It is established that algorithms are capable of accounting for a significantly larger number of variables than traditional methods, which increases the accuracy of comparison. At the same time, several limitations are identified, including issues related to data quality, potential risks of model bias, and difficulties in interpreting the obtained results without a proper theoretical framework. The article proposes an approach to integrating algorithmic analysis with classical tools of political science, which involves step-by-step validation of results and maintaining analytical control by the researcher. The conclusions substantiate that the use of AI does not replace the researcher but changes the nature of their work: the importance of formulating research questions, critically evaluating data, and validating models increases. The effectiveness of comparative studies depends on the combination of algorithmic data processing and theoretical analysis, which allows for more well-grounded conclusions regarding changes in political regimes.
References
1. Hartmann, J., Schwenzow, J., & Witte, M. (2023). The political ideology of conversational AI: Converging evidence on ChatGPT’s orientation. arXiv. https://arxiv.org/abs/2301.01768
2. Tallberg, J., Erman, E., Furendal, M., Geith, J., Klamberg,M., & Lundgren M. (2023). The global governance of artificial intelligence: Next steps for empirical and normative research. arXiv. https://arxiv.org/abs/2305.11528
3. Tararoiev, Y., & Horeva, V. (2024). Vplyv hlobalnykh tendentsii na rozvytok politychnykh elit [The impact of global trends on the development of political elites]. Humanities Studies, 19(96), 83–89. https://doi.org/10.32782/hst-2024-19-96-09 (in Ukrainian)
4. Riezanova, N. (2025). Epistemolohichni mezhi politychnoho znannia: pereosmyslennia metodolohii v umovakh hlobalnoi nestabilnosti [Epistemological limits of political knowledge: Rethinking methodology in conditions of global instability]. Ukrainskyi polityko-pravovyi dyskurs – Ukrainian political and legal discourse, (17). https://doi.org/10.5281/zenodo.17839336 (in Ukrainian)
5. Zaporozhchenko, O. (2025). Filosofiia nauky v epokhu postneklasychnosti: novi aspekty etychnoi vidpovidalnosti [Philosophy of science in the post-nonclassical era: New aspects of ethical responsibility]. Kulturolohichnyi almanakh – Culturological Almanac, (2), 227–235. https://doi.org/10.31392/cult.alm.2025.2.27 (in Ukrainian)
6. Kovalov, O. (2024). Metodolohiia ta praktychna realizatsiia suchasnykh epistemolohichnykh pidkhodiv u naukovii osviti [Methodology and practical implementation of modern epistemological approaches in scientific education]. Kulturolohichnyi almanakh – Culturological Almanac, (3), 228–234. https://doi.org/10.31392/cult.alm.2024.3.26 (in Ukrainian)
7. Udzhmadzhuridze, H. (2024). Politychna stabilnist Ukrainy v umovakh voiennoho stanu: aprobatsiia instytutsiinoho pidkhodu [Political stability of Ukraine under martial law: Testing the institutional approach]. Epistemological Studies in Philosophy, Social and Political Sciences, 7(1), 225–237. https://doi.org/10.15421/342435 (in Ukrainian)
8. Yurkevych, O. (2025). Lohichni doslidzhennia znannia: epistemichna lohika ta interohatyvna epistemolohiia [Logical studies of knowledge: Epistemic logic and interrogative epistemology]. Visnyk Natsionalnoi yurydychnoi akademii Ukrainy imeni Yaroslava Mudroho – Bulletin of the Yaroslav Mudryi National Law Academy of Ukraine, 1(64), 40–54. https://doi.org/10.21564/2663-5704.64.324496 (in Ukrainian)
9. But, S. (2025). Shtuchnyi intelekt u politychnii diialnosti: osnovni napriamky vykorystannia [Artificial intelligence in political activity: Main directions of use]. Publichne upravlinnia i polityka – Public Administration and Politics, 5(9). https://doi.org/10.70651/3041-2498/2025.5.04 (in Ukrainian)
10. Ali, H., Farman, H., Yar, H., Khan, Z., Habib, S., & Ammar, A. (2022). Deep learning-based election results prediction using Twitter activity. Soft Computing, 26(16), 7535–7543. https://doi.org/10.1007/s00500-021-06569-5
11. Amoore, L. (2023). Machine learning political orders. Review of International Studies, 49(1), 20–36. https://doi.org/10.1017/S0260210522000031
12. García-Díaz, J. A., Colomo-Palacios, R., & Valencia-García, R. (2022). Psychographic traits identification based on political ideology: An author analysis study on Spanish politicians’ tweets posted in 2020. Future Generation Computer Systems, (130), 59–74. https://doi.org/10.1016/j.future.2021.12.011
13. Muchlinski, D., Yang, X., Birch, S., Macdonald, C., & Ounis, I. (2021). We need to go deeper: Measuring electoral violence using convolutional neural networks and social media. Political Science Research and Methods, 9(1), 122–139. https://doi.org/10.1017/psrm.2020.32
14. Rasikh, S. (2025). Democracy, development and AI: A comparative study of political systems, electoral processes and economic expansion. Journal of Political Science, 2(1), 35–40. https://doi.org/10.54536/jpsir.v2i1.3802
15. Umran, Z. M., & Klioy, L. K. (2024). A geopolitical analysis of indicators of democratic transformation in Iraq (Indicator of the supremacy of democratic political culture as a model). Pakistan Journal of Life and Social Sciences, 22(1), 3666–3671. https://doi.org/10.57239/PJLSS-2024-22.1.00267
16. Doroshenko, L. (2022). Populists and social media campaigning in Ukraine: The election of Volodymyr Zelensky. In D. Taras & R. Davis (Eds.), Electoral campaigns, media, and the new world of digital politics (pp. 221–243). University of Michigan Press. https://www.jstor.org/content/oa_chapter_edited/10.3998/mpub.12013603.14?seq=1
17. Soltanifar, M., Hughes, M., & Göcke, L. (2021). Digital entrepreneurship: Impact on business and society. Springer Nature. https://doi.org/10.1007/978-3-030-53914-6
18. Analytical report “Opinions and views of Ukrainians on state electronic services in 2023” (2024). United Nations Development Programme. https://www.undp.org/ukraine/publications/analytical-report-opinions-and-views-ukrainians-state-electronic-services-2023
19. Castillo-Esparcia, A., Caro-Castaño, L., & Almansa-Martínez, A. (2023). Evolution of digital activism on social media: Opportunities and challenges. El Profesional de la Información, 32(3). https://doi.org/10.3145/epi.2023.may.03
20. Tsyhvintev, I. (2024). Politychna kultura v epokhu tsyfrovizatsii: novi doslidnytski instrumenty [Political culture in the era of digitalization: New research tools]. Politychni doslidzhennia – Political Studies, 2(8), 137–155. https://doi.org/10.53317/2786-4774-2024-2-7 (in Ukrainian)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2026 Liudmyla Novoskoltseva, Denys Demidov