POLITICAL-GEOGRAPHIC RESEARCH USING ARTIFICIAL INTELLIGENCE: NEURAL NETWORK CAPABILITIES AND LIMITATIONS
DOI:
https://doi.org/10.17072/2218-1067-2026-1-115-126Keywords:
geographical conflict study, electoral geography, world order, anti-corruption geography, state border, administrative-territorial division, cross-border interaction, spatial diffusion of innovations, artificial neural networkAbstract
The study assesses the possibilities and limitations of neural network algorithms in political-geographic research using a global selection of journal articles. It examined the nature of artificial neural networks, compiled a database of relevant studies, evaluated their heuristic capabilities for current and future research, and identified methodological limitations. Using an author-developed semantic search algorithm based on machine learning, over seventy journal articles were retrieved, with their distribution by year and country analyzed. These articles covered conflict studies, elections, world order, and anti-corruption within political geography. They employed single- and multi-layer perceptrons, self-organizing maps, convolutional, recurrent, and graph neural networks. These algorithms enabled predictions of armed conflict timing and location, election outcomes, shifts in the balance of power, and territorial corruption risks. They are characterized by self-learning, detection of complex nonlinear dependencies, simultaneous analysis of diverse data types, fault tolerance, noise resistance, and high performance. Future applications in border studies, regional studies, cross-border interactions, and the diffusion of political ideas were outlined. Analysis of the articles revealed ten main limitations of artificial neural networks, and six initiatives were proposed to address them in future research. These findings guide the emerging field of neural network analysis in political-geographic processesReferences
Блануца, В. И. (2021) ‘Интеллектуальный анализ данных в общественно-географических исследованиях’, Общественные науки и современность, 6, cc. 150–164. [Blanutsa, V. I. (2021) ‘Data mining in socio-geographical research’ [Intellektual'nyj analiz dannyh v obshchestvenno-geograficheskih issledovaniyah], Social Sciences and Modernity, 6, pp. 150–164. (In Russ.)]. DOI: 10.31857/S086904990017878-7
Блануца, В. И. (2022) Общественная география: цифровые приоритеты XXI века. Москва: ИНФРА-Мб 252 с. [Blanutsa, V. I. (2022) Human Geography: Digital Priorities of the 21st Century [Obshchestvennaya geografiya: cifrovye prioritety XXI veka]. Moscow: INFRA-M Publ, 252 p. (In Russ.)].
Блануца, В. И. (2024) Общественная география после 2030 года: контуры новых направлений. Москва: ИНФРА-М, 251 c. [Blanutsa, V. I. (2024) Human Geography after 2030: Outlines of New Directions [Obshchestvennaya geografiya posle 2030 goda: kontury novyh napravlenij]. Moscow: INFRA-M Publ, 251 p. (In Russ.)].
Блануца, В. И. (2025) ‘Создание первых автономных систем интернета в Сибири как пространственная диффузия инноваций’, Пространственная экономика, 21(1), cc. 7–32. [Blanutsa, V. I. (2025) ‘Creating the first autonomous systems of Internet in Siberia as a spatial diffusion of innovations’ [Sozdanie pervyh avtonomnyh sistem interneta v Sibiri kak prostranstvennaya diffuziya innovacij], Spatial Economics, 21(1), pp. 7–32. (In Russ.)]. DOI: 10.14530/se.2025.1.007-032
Окунев, И. Ю., Шестакова, М. Н. (2022) Политическая география: Современная российская школа: Хрестоматия. Москва: Аспект Пресс, 544 c. [Okunev, I. Yu., Shestakova, M. N. (2022) Political Geography: Modern Russian School: Anthology [Politicheskaya geografiya: Sovremennaya rossijskaya shkola: Hrestomatiya]. Moscow: Aspect Press, 544 p. (In Russ.)].
Петрунин, Ю. Ю. (2009) ‘Исследование электорального поведения: самоорганизующиеся карты Кохонена versus статистического анализа’, Вестник Московского университета. Сер. 21. Управление (государство и общество), 3, cc. 45–55. [Petrunin, Yu. Yu. (2009) ‘Research of electoral behavior: Kohonen’s self-organizing maps versus statistical analysis’ [Issledovanie elektoral'nogo povedeniya: samoorganizuyushchiesya karty Kohonena versus statisticheskogo analiza], Bulletin of Moscow University, Ser. 21, Management (State and Society), 3, pp. 45–55. (In Russ.)].
Amoore, L. (2024) ‘The deep border’, Political Geo¬graphy, 109, e102547. DOI: 10.1016/j.polgeo.2021.102547
Amoore, L., Campolo, A., Jacobsen, B., et al. (2024) ‘A world model: On the political logics of generative AI’, Political Geography, 113, e103134. DOI: 10.1016/j.polgeo.2024.103134
Barthwal, A., Bhatt, M., Avikal, S., et al. (2025) ‘Machine learning-based prediction models for electoral outcomes in India: A comparative analysis of exit polls from 2014–2021’, Quality & Quantity, 59, pp. 313–338. DOI: 10.1007/s11135-024-01937-3
Blatter, J., Portmann, L., Rausis, F. (2022) ‘Theorizing policy diffusion: From a patchy set of mechanisms to a paradigmatic typology’, Journal of European Public Policy, 29(6), pp. 805–825. DOI 10.1080/13501763.2021.1892801
Brandt, P. T., D’Orazio, V., Khan, L., et al. (2022) ‘Conflict forecasting with event data and spatio-temporal graph convolutional networks’, International Interaction, 48(4), pp. 800–822. DOI 10.1080/03050629.2022.2036987
Breiman, L. (2001) ‘Random forests’, Machine Learning, 45(1), pp. 5–32.
Brito, K. and Adeodato, P. J. L. (2023) ‘Machine learning for predicting elections in Latin America based on social media engagement and polls’, Government Information Quarterly, 40(1), e101782. DOI: 10.1016/j.giq.2022.101782
Buscema, M., Ferilli, G., Sacco, P. L. (2017) ‘What kind of “world order”? An artificial neural networks approach to intensive data mining’, Technological Forecasting and Social Change, 117, pp. 46–56.
Buscema, M., Ferilli, G., Sacco, P. L. (2018) ‘The meta-geography of the open society: An Auto-CM ANN approach’, Expert Systems with Applications, 99, pp. 12–24.
Chatsiou, K., Mikhaylov, S. J. (2025) ‘Deep learning for political science”, in: Curini, L. and Franzese, R. (eds.) The SAGE Handbook of Research Methods in Political Science and International Relations. London: SAGE Publ., vol. 2, pp. 1053–1078.
Da Silva, I. N., Spatti, D. H., Flauzino, R. A., et al. (2017) Artificial Neural Networks: A Practical Course. Cham: Springer, 307 p.
De Lombaerde, P., Naeher, D., Vo, H.T, et al. (2023) ‘Regional economic integration and machine learning: Policy insights from the review of literature’, Journal of Policy Modeling, 45(5), pp. 1077–1097. DOI: 10.1016/j.jpolmod.2023.07.001
D’Orazio, V., Lin, Y. (2022) ‘Forecasting conflict in Africa with automated machine learning systems’, International Interactions, 48(4), pp. 714–738. DOI: 10.1080/03050629.2022.2017290
Du, Y., Ding, N., Lv, H. (2025) ‘Spatio-temporal prediction of terrorist attacks based on GCN-LSTM’, Journal of Safety Science and Resilience, 6(2), pp. 186–195. DOI: 10.1016/j.jnlssr.2025.02.005
Durand, F., Decoville, A. (2020) ‘A multidimensional measurement of the integration between European border regions’, Journal of European Integration, 42(2), pp. 163–178. DOI: 10.1080/07036337.2019.1657857
Erspamer, C., Torre, F.D., Massini, G., et al. (2022) ‘Global world (dis-)order? Analyzing the dynamic evolution of the micro-structure of multipolarism by means of an unsupervised neural network approach’, Technological Forecasting and Social Change, 175, e121351. DOI: 10.1016/j.techfore.2021.121351
Ettensperger, F. (2022) ‘Forecasting conflict using a diverse machine-learning ensemble: Ensemble averaging with multiple tree-based algorithms and variance promoting data configurations’, International Interactions, 48(4), pp. 555–578. DOI: 10.1080/03050629.2022.1993209
Ghahari, S., Queiroz, C., Labi, S., et al. (2021) ‘Cluster forecasting of corruption using non¬linear autoregressive models with exo¬ge¬nous variables (NARX) – An artificial neural network analysis’, Sustainability, 13(20), e11366. DOI: 10.3390/su132011366
Gilardi, F., Wasserfallen, F. (2019) ‘The politics of policy diffusion’, European Journal of Political Research, 58(4), pp. 1245–1256.
Goodman, S., Yishay, A. B., Runfola, D. (2024) ‘Spatiotemporal prediction of conflict fatality risk using convolutional neural networks and satellite imagery’, Remote Sensing, 16(18), e3411. DOI: 10.3390/rs16183411
Grekousis, G. (2019) ‘Artificial neural networks and deer learning in urban geography: A systematic review and meta-analysis’, Computers, Environment and Urban Systems, 74, pp. 244–256.
Hashemi, M. (2023) ‘Geographical visualization of tweets, misinformation, and extremism during the USA 2020 presidential election using LSTM, NLP, and GIS’, Journal of Big Data, 10, e125. DOI: 10.1186/s40537-023-00797-2
Hassoun, M. H. (1995) Fundamentals of Artificial Neu¬ral Networks. Cambridge: MIT Press, 511 p.
Janowicz, K., Gao, S., McKenzie, G., et al. (2020) ‘GeoAI: Spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond’, International Journal of Geographical Information Science, 34(4), pp. 625–636. DOI: 10.1080/13658816.2019.1684500
Jiang, D., Wu, J., Ding, F., et al. (2023) ‘An integrated deep-learning and multi-level framework for understanding the behavior of terrorist groups’, Heliyon, 9(8), e18895. DOI: 10.1016/j.heliyon.2023.18895
Kohonen, T. (2001) Self-Organizing Maps. 3rd ed. Berlin: Springer, 501 p.
Koutidis, G., Loumponias, K., Tsikrika, T., et al. (2024) ‘Towards AI-driven prediction of terrorism risk based on the analysis of localized web news’, IEEE Access, 12, pp. 167288–167299. DOI: 10.1109/ACCESS.2024.3485913
LeCun, Y., Boser, B., Denker, J. S., et al. (1989) ‘Backpropagation applied to handwritten zip code recognition’, Neural Computation, 1(4), pp. 541–551.
Lemke, N., Trein, P., Varone, F. (2024) ‘Defining artificial intelligence as a policy problem: A discourse network analysis from Germany’, European Policy Analysis, 10(2), pp. 162–187. DOI: 10.1002/epa2.1203
Lima, M. S. M., Delen, D. (2020) ‘Predicting and explaining corruption across countries: A machine learning approach’, Government Information Quarterly, 37(1), e101407. DOI: 10.1016/j.giq.2019.101407
Liu, R., Yao, X., Guo, C., et al. (2021) ‘Can we forecast presidential election using Twitter data? An integrative modelling approach’, Annals of GIS, 27(1), pp. 43–56. DOI: 10.1080/19475683.2020.1829704
López-Iturriaga, F. J., Sanz, I. P. (2018) ‘Predicting public corruption with neural networks: An analysis of Spanish provinces’, Social Indicators Research, 140, pp. 975–998.
Malone, I. (2022) ‘Recurrent neural networks for conflict forecasting’, International Interaction, 48(4), pp. 614–632. DOI: 10.1080/03050629.2022.2016736
Marwala, T., Lagazio, M., Tettey, T. (2009) ‘An integrated human-computer system for controlling interstate disputes’, International Journal of Computers and Applications, 31(4), pp. 239–246.
Menga, F., Nagel, C., Grove, K., et al. (eds.) (2024) Political Geography in Practice: Theories, Approaches, Methodologies. Cham: Palgrave Macmillan, 301 p.
Michalak, P. (2019) ‘Application of artificial neural networks in predicting voter turnout based on the analysis of demographic data’, Polish Cartographical Review, 51(3), pp. 109–116.
Mienye, I. D., Swart, T. G., Obaido, G. (2024) ‘Recurrent neural networks: A comprehensive review of architectures, variants, and applications’, Information, 15(9), e517. DOI: 10.3390/info15090517
Neme, A., Hernández, S., Neme, O. (2011) ‘An electoral preferences model based on self-organizing maps’, Journal of Computational Science, 2(4), pp. 345–352.
Qin, S., Wang, Y., Yang, X. (2023) ‘Policy innovation diffusion and PPP spatial distribution’, China Finance and Economic Review, 11(3), pp. 110–129. DOI: 10.1515/cfer-2022-0019
Radford, B. J. (2022) ‘High resolution conflict forecasting with spatial convolutions and long short-term memory’, International Interaction, 48(5), pp. 739–758. DOI: 10.1080/03050629.2022.2031182
Raduleścu, M., Banica, L. (2014) ‘Neural networks-based forecasting regarding the convergence process of CEE countries to the Eurozone’, Transylvanian Review of Administrative Sciences, 42, pp. 225–246.
Ravi, S. K., Chaturvedi, S., Rastogi, N., et al. (2022) ‘A framework for voting behavior prediction using spatial data’, International Journal of Innovative Research in Computer Science and Technology, 10(2), pp. 19–28. DOI: 10.55524/ijircst.2022.10.2.4
Saidi, F., Trabelsi, Z. (2022) ‘A hybrid deep learning-based framework for future terrorist activities modeling and prediction’, Egyptian Informatics Journal, 23(3), pp. 437–446. DOI: 10.1016/j.eij.2022.04.001
Sarlin, P. (2011) ‘Evaluating a self-organizing map for clustering and visualizing optimal currency area criteria’, Economics Bulletin, 31(2), pp. 1483–1495.
Schrodt, P. A. (1991) ‘Prediction of interstate conflict outcomes using a neural network’, Social Science Computer Review, 9(3), pp. 359–380.
Schweinfurth, J. (2025) Artificial Neural Network Architectures. New Delhi: DPH, 228 p.
Squire, R., Jackman, A. (2024) Political Geography: Approaches, Concepts, Futures. London: SAGE Publ, 256 p.
Stoffa, J., Lisbona, R., Farrar, C., et al. (2018) ‘Predicting how U.S. counties will vote in presidential elections through analysis of socio-economic factors, voting heuristics, and party platforms’, SMU Data Science Review, 1(1), e4.
Törnberg, P., Söderström, O., Barella, J., et al. (2025) ‘Artificial intelligence and the state: Seeing like an artificial neural network’, Big Data & Society, 12(2), pp. 1–14. DOI: 10.1177/20539517251338773
Vapnik, V. N. (1998) Statistical Learning Theory. New York: John Wiley and Sons, 768 p.
Wang, S., Huang, X., Liu, P., et al. (2024) ‘Mapping the landscape and roadmap of geospatial artificial intelligence (GeoAI) in quantitative human geography: An extensive systematic review’, International Journal of Applied Earth Observation and Geoinformation, 128, e103734. DOI: 10.1016/j.jzg.2024.103734
Warf, B. (2016) ‘Global geographies of corruption’, GeoJournal, 81(5), pp. 657–669.
Wilson, T. M. (ed.) (2025). Border Studies: A Multidisciplinary Approach. Cheltenham: Edward Elgar Publ, 350 p.
Wordliczek, L. (2023) ‘Neural network and political science: Testing the methodological frontiers’, EMPIRIA. Revista de Metodologia de Ciencias Sociales, 57, pp. 37–62. DOI: 10.5944/empiria.57.2023.36429
Wu, L., Cui, P., Pei, J., et al. (2022) Graph Neural Networks: Foundation, Frontiers, and Applications. Singapore: Springer, 689 p
Downloads
Published
How to Cite
Issue
Section
License
The author grants the Publisher of the journal (Perm State University) the right to use their article in the journal, as well as to include the text of the abstract, the full text of the article and information about authors in the "Russian Science Citation Index" (RSCI).
The author agrees to the processing of personal data.
The right to use the journal as a whole belongs to the Publisher and acts indefinitely on the territory of the Russian Federation and beyond in accordance with cl. 1260 of the Russian Federation Civil Code.
There is no author's fee paid for providing the above rights by the author.
The author of the article included in the journal retains the exclusive right to it, regardless of the Publisher's right to use the journal as a whole:
a. The authors retain their copyrights to the article and transfer the right of the first publication along with the article to the journal, while also licensing it on the terms of the Creative Commons Attribution License, which allows others to distribute this article with the obligatory indication of authorship of the article and reference to the original publication in this journal.
b. The authors retain the right to enter into separate, additional contractual agreements for the non-exclusive dissemination of the version of the text published by this journal (for example, post it in a university archive or publish it in a book), with reference to the original publication in this journal.
c. d. Authors are allowed to post their text on the Internet (for example, in a university archive or on their personal website) before and during the review process by this journal, as this can lead to a fruitful discussion and to higher number of the references to this published work (Please refer to The Effect of Open Access).
Submission of an article by the author implies that they agree for it to be used by the Publisher on the above conditions and to be included in the RSCI system. It also implicates that the author is aware of the terms of its use. The information about the author sent to the Publisher, including by e-mail, is also considered as such consent.
The editorial board posts the full text of the article on the Perm State University site: http://www.psu.ru and in the OJS system at http://press.psu.ru
The publication fee is not collected and fees are not paid. The author's copy is sent to the author to the address provided by them.
