politscienceПолитическая наукаPolitical science1998-1775ИНИОН РАН10.31249/poln/2023.04.09politscience-997Research ArticleПЕРВАЯ СТЕПЕНЬОб опыте применения больших данных в политической наукеOn the experience of applying Big data in political scienceКочедыковИ. Е.KochedykovL. E.

Кочедыков Иван Евгеньевич, магистр, аспирант

Москва

Kochedykov Ivan

Moscow

Kochedykov.ivan@gmail.comНациональный исследовательский университет «Высшая школа экономики»РоссияHSE UniversityRussian Federation20232111202304Политическая наука в условиях социальных и технологических изменений226251Copyright © Кочедыков И.Е., 20232023Кочедыков И.Е.Kochedykov L.E.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.politnauka.ru/jour/article/view/997

Данная обзорная статья посвящена анализу успехов и проблем применения больших данных в политической науке. В первой части обсуждаются онтологические эпистемологические предпосылки использования Big data и машинного обучения в политических исследованиях. Во второй части автор проводит обзор репрезентативных результатов политологических исследований, произведенных с использованием больших данных. Третья часть статьи посвящена критике и определению пределов использования Big data в политических исследованиях. Автор показывает, что кроме чисто технических проблем, связанных, например, с неполнотой имеющихся данных, искажениями из-за присутствия ботов, существует серьезные ограничения возможностей применения больших данных для анализа политических действий, которые имеют диспозициональный характер.

The review article is devoted to the analysis of successes and challenges of Big Data application in political science. The first part discusses the ontological and epistemological foundations of Big Data and machine learning application in political science. In the second part, the author reviews representative results of political science research using Big Data. The third part deals with criticism and limitations of Big Data in political research. The author shows besides purely technical problems, such as incompleteness of available data, distortions due to the presence of bots, there are sufficient limitations to the application of big data for analyzing dispositional political actions.

Big dataбольшие данныеалгоритмымашинное обучениеонтология и эпистемология Больших данныхтеория действияBig dataalgorithmsmachine learningontology and epistemology of big datatheory of actionReferencesАхременко А.С., Петров А.П. Гнев, идентичность или вера в успех? Динамика мотивации и участия в белорусских протестах 2020 года // Полис. Политические исследования. – 2023. – № 2. – С. 138–153. DOI: https://doi.org/10.17976/jpps/2023.02.10Anderson C. The end of theory: The data deluge makes the scientific method obsolete. Wired magazine. 2008, July 16, P. 1–2. Mode of access: http://statlit.org/pdf/2008EndOfTheory-DataDelugeMakesScientificMethodObsolete-WiredMagazine.pdf (accessed: 10.07.2023).Вахштайн В.С.1 Техника, или Обаяние прогресса. – СПб: Изд-во Европейского университета в Санкт-Петербурге, 2021. – 156 с.Akhremenko A., Petrov A. Anger, identity or efficacy belief? Dynamics of motivation and participation in 2020 Belarusian protests. Polis. Political Studies, 2023, N 2, P. 138–153. (In Russ.) DOI: https://doi.org/10.17976/jpps/2023.02.10Чизмен Н., Клаас Б. Как почти честно выиграть выборы. – М.: Бомбора: 2021, 320 с.Ash E., Gauthier G., Widmer P. Relatio: Text semantics capture political and economic narratives. Political Analysis. 2023, First View. P. 1–18. DOI: https://doi.org/10.1017/pan.2023.8Ын А., Су К. Теоретический минимум по Big Data. Всё, что нужно знать о больших данных. – СПб.: Питер, 2022. – 208 c.Athey S. Beyond prediction: Using big data for policy problems. Science. 2017. N 355, P. 483–485. DOI: https://doi.org/10.1126/science.aal432Barclay F., Pichandy C., Venkat A., Sudhakaran S. India 2014: Facebook ‘like’ as a predictor of election outcomes. Asian Journal of Political Science. 2015, Vol 23, N 2, P. 134–160. DOI: https://doi.org/10.1080/02185377.2015.1020319Barclay F., Pichandy C., Venkat A., Sudhakaran S. India 2014: Facebook ‘like’ as a predictor of election outcomes. Asian Journal of Political Science. 2015, Vol 23, N 2, P. 134–160. DOI: https://doi.org/10.1080/02185377.2015.1020319Benoit K., Munger K., Spirling A. Measuring and explaining political sophistication through textual complexity. American Journal of Political Science. 2019, Vol. 63, N 2, P. 491–508. DOI: https://doi.org/10.1111/ajps.12423Benoit K., Munger K., Spirling A. Measuring and explaining political sophistication through textual complexity. American Journal of Political Science. 2019, Vol. 63, N 2, P. 491–508. DOI: https://doi.org/10.1111/ajps.12423Bond R., Messing S. Quantifying social media’s political space: Estimating ideology from publicly revealed preferences on Facebook. American Political Science Review. 2015, Vol. 109, N 1, P. 62–78. DOI: https://doi.org/10.1017/S0003055414000525Bond R., Messing S. Quantifying social media’s political space: Estimating ideology from publicly revealed preferences on Facebook. American Political Science Review. 2015, Vol. 109, N 1, P. 62–78. DOI: https://doi.org/10.1017/S0003055414000525Bonica A. A data-driven voter guide for US elections: Adapting quantitative measures of the preferences and priorities of political elites to help voters learn about candidates. RSF: The Russell Sage Foundation Journal of the Social Sciences. 2016, Vol. 2, N 7, P. 11–32. DOI: https://doi.org/10.7758/rsf.2016.2.7.02Bonica A. A data-driven voter guide for US elections: Adapting quantitative measures of the preferences and priorities of political elites to help voters learn about candidates. RSF: The Russell Sage Foundation Journal of the Social Sciences. 2016, Vol. 2, N 7, P. 11–32. DOI: https://doi.org/10.7758/rsf.2016.2.7.02Boullier D. The social sciences and the traces of big data. Revue francaise de science politique. 2015, Vol. 65, N 5, P. 805–828. DOI: https://doi.org/10.48550/arXiv.1607.05034Boullier D. The social sciences and the traces of big data. Revue francaise de science politique. 2015, Vol. 65, N 5, P. 805–828. DOI: https://doi.org/10.48550/arXiv.1607.05034Boyd D., Crawford K. Critical questions for big data: Provocations for a cultural, technological, and scholarly phenomenon. Information, communication & society. 2012, Vol. 15, N 5, P. 662–679. DOI: https://doi.org/10.1080/1369118X.2012.678878Boyd D., Crawford K. Critical questions for big data: Provocations for a cultural, technological, and scholarly phenomenon. Information, communication & society. 2012, Vol. 15, N 5, P. 662–679. DOI: https://doi.org/10.1080/1369118X.2012.678878Ceron A., Curini L., Iacus S. Using sentiment analysis to monitor electoral campaigns: Method matters – evidence from the United States and Italy. Social Science Computer Review. 2015, Vol. 33, N 1, P. 3–20. DOI: https://doi.org/10.1177/0894439314521983Ceron A., Curini L., Iacus S. Using sentiment analysis to monitor electoral campaigns: Method matters – evidence from the United States and Italy. Social Science Computer Review. 2015, Vol. 33, N 1, P. 3–20. DOI: https://doi.org/10.1177/0894439314521983Cheeseman N., Klaas B. How to rig and election. Moscow: Bombora, 2021, 320 p. (In Russ.).Cheeseman N., Klaas B. How to rig and election. Moscow: Bombora, 2021, 320 p. (In Russ.).Ceron A., Curini L., Iacus S. Social media and elections: A meta-analysis of onlinebased electoral forecasts. In: Arzheimer K., Evans J., Lewis-Beck M.S. (eds.) Sage Handbook of electoral behaviour. London: SAGE Publications Ltd, 2017, P. 883– 903. DOI: https://doi.org/10.4135/9781473957978Ceron A., Curini L., Iacus S. Social media and elections: A meta-analysis of onlinebased electoral forecasts. In: Arzheimer K., Evans J., Lewis-Beck M.S. (eds.) Sage Handbook of electoral behaviour. London: SAGE Publications Ltd, 2017, P. 883– 903. DOI: https://doi.org/10.4135/9781473957978Chatsiou K., Mikhaylov S.J. Deep learning for political science. arXiv preprint arXiv:2005.06540. 2020. Mode of access: https://arxiv.org/abs/2005.06540 (accessed: 10.07.2023).Chatsiou K., Mikhaylov S.J. Deep learning for political science. arXiv preprint arXiv:2005.06540. 2020. Mode of access: https://arxiv.org/abs/2005.06540 (accessed: 10.07.2023).Colaresi M., Mahmood Z. Do the robot: Lessons from machine learning to improve conflict forecasting. Journal of Peace Research. 2017, Vol. 54, N 2, P. 193–214. DOI: https://doi.org/10.1177/0022343316682065Colaresi M., Mahmood Z. Do the robot: Lessons from machine learning to improve conflict forecasting. Journal of Peace Research. 2017, Vol. 54, N 2, P. 193–214. DOI: https://doi.org/10.1177/0022343316682065Conover M.D., Davis C., Ferrara E., McKelvey K., Menczer F., Flammini A. The geospatial characteristics of a social movement communication network. PloS one. 2013, Vol. 8, N 3. DOI: https://doi.org/10.1371/journal.pone.0055957Conover M.D., Davis C., Ferrara E., McKelvey K., Menczer F., Flammini A. The geospatial characteristics of a social movement communication network. PloS one. 2013, Vol. 8, N 3. DOI: https://doi.org/10.1371/journal.pone.0055957Gandomi A., Haider M. Beyond the hype: big data concepts, methods, and analytics. International journal of information management. 2015, Vol. 35, N 2, P. 137–144. DOI: https://doi.org/10.1016/j.ijinfomgt.2014.10.007Gandomi A., Haider M. Beyond the hype: big data concepts, methods, and analytics. International journal of information management. 2015, Vol. 35, N 2, P. 137–144. DOI: https://doi.org/10.1016/j.ijinfomgt.2014.10.007Grimmer J., Stewart B.M. Text as data: The promise and pitfalls of automatic content analysis methods for political texts. Political analysis. 2013, Vol. 21 N. 3, P. 267– 297. DOI: doi:10.1093/pan/mps028Grimmer J., Stewart B.M. Text as data: The promise and pitfalls of automatic content analysis methods for political texts. Political analysis. 2013, Vol. 21 N. 3, P. 267– 297. DOI: doi:10.1093/pan/mps028Grossman J., Pedahzur A. Political science and big data: Structured data, unstructured data, and how to use them. Political science quarterly. 2020, Vol. 135, N 2, P. 225– 257. DOI: https://doi.org/10.1002/polq.13032Grossman J., Pedahzur A. Political science and big data: Structured data, unstructured data, and how to use them. Political science quarterly. 2020, Vol. 135, N 2, P. 225– 257. DOI: https://doi.org/10.1002/polq.13032Karstens M., Soules M.J., Dietrich N. On the Replicability of Data Collection Using Online News Databases. PS: Political Science & Politics. 2023, Vol. 56, N 2, P. 265–272. DOI:10.1017/S1049096522001317Karstens M., Soules M.J., Dietrich N. On the Replicability of Data Collection Using Online News Databases. PS: Political Science & Politics. 2023, Vol. 56, N 2, P. 265–272. DOI:10.1017/S1049096522001317Katagiri A., Min E. The credibility of public and private signals: A document-based approach. American Political Science Review. 2019, Vol. 113, N 1, P. 156–172. DOI: https://doi.org/10.1017/S0003055418000643Katagiri A., Min E. The credibility of public and private signals: A document-based approach. American Political Science Review. 2019, Vol. 113, N 1, P. 156–172. DOI: https://doi.org/10.1017/S0003055418000643Sang E.T., Bos J. Predicting the 2011 Dutch senate election results with twitter. Proceedings of the workshop on semantic analysis in social media. 2012. – Mode of access: https://www.let.rug.nl/bos/pubs/TjongBos2012EACL.pdf (accessed: 11.06.2023).Sang E.T., Bos J. Predicting the 2011 Dutch senate election results with twitter. Proceedings of the workshop on semantic analysis in social media. 2012. – Mode of access: https://www.let.rug.nl/bos/pubs/TjongBos2012EACL.pdf (accessed: 11.06.2023).King G., Pan J., Roberts M.E. How censorship in China allows government criticism but silences collective expression. American political science Review. 2013, Vol. 107, N 2, P. 326–343. DOI: https://doi.org/10.1017/S0003055413000014King G., Pan J., Roberts M.E. How censorship in China allows government criticism but silences collective expression. American political science Review. 2013, Vol. 107, N 2, P. 326–343. DOI: https://doi.org/10.1017/S0003055413000014Kitchin R., McArdle G. What makes Big Data, Big Data? Exploring the ontological characteristics of 26 datasets. Big Data & Society. 2016, Vol. 3, N 1. DOI: https://doi.org/10.1177/205395171663113Kitchin R., McArdle G. What makes Big Data, Big Data? Exploring the ontological characteristics of 26 datasets. Big Data & Society. 2016, Vol. 3, N 1. DOI: https://doi.org/10.1177/205395171663113Lazer D., Radford J. Data ex machina: introduction to big data. Annual Review of Sociology. 2017, Vol. 43, P. 19–39. DOI: https://doi.org/10.1146/annurev-soc-060116-053457Lazer D., Radford J. Data ex machina: introduction to big data. Annual Review of Sociology. 2017, Vol. 43, P. 19–39. DOI: https://doi.org/10.1146/annurev-soc-060116-053457Lizardo O. Habit and the Explanation of Action. Journal for the Theory of Social Behaviour. 2021, Vol. 51, N 3, P. 391–411. DOI: https://doi.org/10.1111/jtsb.12273Lizardo O. Habit and the Explanation of Action. Journal for the Theory of Social Behaviour. 2021, Vol. 51, N 3, P. 391–411. DOI: https://doi.org/10.1111/jtsb.12273Meng X-L. Statistical paradises and paradoxes in big data (i) law of large populations, big data paradox, and the 2016 US presidential election. The Annals of Applied Statistics. 2018, Vol. 12, N 2, P. 685–726. DOI: https://doi.org/10.1214/18-AOAS1161SFMeng X-L. Statistical paradises and paradoxes in big data (i) law of large populations, big data paradox, and the 2016 US presidential election. The Annals of Applied Statistics. 2018, Vol. 12, N 2, P. 685–726. DOI: https://doi.org/10.1214/18-AOAS1161SFMontgomery J.M., Olivella S., Potter J.D., Crisp B.F. An informed forensics approach to detecting vote irregularities. Political Analysis. 2015, Vol. 23, N 4, P. 488–505. DOI: https://doi.org/10.1093/pan/mpv023Montgomery J.M., Olivella S., Potter J.D., Crisp B.F. An informed forensics approach to detecting vote irregularities. Political Analysis. 2015, Vol. 23, N 4, P. 488–505. DOI: https://doi.org/10.1093/pan/mpv023Mueller H., Rauh C. Reading between the lines: Prediction of political violence using newspaper text. American Political Science Review. 2018, Vol. 112, N 2, P. 358– 375. DOI: https://doi.org/10.1017/S0003055417000570Mueller H., Rauh C. Reading between the lines: Prediction of political violence using newspaper text. American Political Science Review. 2018, Vol. 112, N 2, P. 358– 375. DOI: https://doi.org/10.1017/S0003055417000570Ng A., Soo K. Numsense! Data science for the layman: no math added. Piter, 2022, 208 p. (In Russ.).Ng A., Soo K. Numsense! Data science for the layman: no math added. Piter, 2022, 208 p. (In Russ.).Park B., Greene K., Colaresi M. Human rights are (increasingly) plural: Learning the changing taxonomy of human rights from large-scale text reveals information effects. American Political Science Review. 2020, Vol. 14, N 3, P. 888–910. DOI: https://doi.org/10.1017/S0003055420000258Park B., Greene K., Colaresi M. Human rights are (increasingly) plural: Learning the changing taxonomy of human rights from large-scale text reveals information effects. American Political Science Review. 2020, Vol. 14, N 3, P. 888–910. DOI: https://doi.org/10.1017/S0003055420000258Pavan E., Mainardi A. Striking, Marching, Tweeting. Studying how online networks change together with movements. Partecipazione e conflitto. 2018, Vol. 11, N 2, P. 394–422. DOI: 10.1285/i20356609v11i2p394Pavan E., Mainardi A. Striking, Marching, Tweeting. Studying how online networks change together with movements. Partecipazione e conflitto. 2018, Vol. 11, N 2, P. 394–422. DOI: 10.1285/i20356609v11i2p394Pietsch W. Aspects of theory-ladenness in data-intensive science. Philosophy of Science. 2015, Vol. 82, N 5, P. 905–916. DOI: https://doi.org/10.1086/683328Pietsch W. Aspects of theory-ladenness in data-intensive science. Philosophy of Science. 2015, Vol. 82, N 5, P. 905–916. DOI: https://doi.org/10.1086/683328Pietsch W. On the epistemology of data science: Conceptual tools for a new inductivism. Berlin; Heidelberg: Springer-Verlag. 2021, Vol. 148, 295 p. DOI: https://doi.org/10.1007/978-3-030-86442-2Pietsch W. On the epistemology of data science: Conceptual tools for a new inductivism. Berlin; Heidelberg: Springer-Verlag. 2021, Vol. 148, 295 p. DOI: https://doi.org/10.1007/978-3-030-86442-2Reis, J., Correia A., Murai F., Veloso ABenevenuto F. Supervised learning for fake news detection. IEEE Intelligent Systems. 2019, Vol. 34, N 2, P. 76–81. DOI: https://doi.org/10.1109/MIS.2019.2899143Reis, J., Correia A., Murai F., Veloso ABenevenuto F. Supervised learning for fake news detection. IEEE Intelligent Systems. 2019, Vol. 34, N 2, P. 76–81. DOI: https://doi.org/10.1109/MIS.2019.2899143Rettberg J.W. Algorithmic failure as a humanities methodology: Machine learning's mispredictions identify rich cases for qualitative analysis. Big Data & Society. 2022, Vol. 9, N 2. DOI: https://doi.org/10.1177/20539517221131290Rettberg J.W. Algorithmic failure as a humanities methodology: Machine learning's mispredictions identify rich cases for qualitative analysis. Big Data & Society. 2022, Vol. 9, N 2. DOI: https://doi.org/10.1177/20539517221131290Rotman A., Shalev M. Using location data from mobile phones to study participation in mass protests. Sociological Methods & Research. 2022, Vol. 51, N 3, P. 1357–1412. DOI: https://doi.org/10.1177/0049124120914926Rotman A., Shalev M. Using location data from mobile phones to study participation in mass protests. Sociological Methods & Research. 2022, Vol. 51, N 3, P. 1357–1412. DOI: https://doi.org/10.1177/0049124120914926Salganik M.J. Bit by bit: Social research in the digital age. Princeton: Princeton University Press, 2019, 448 p.Salganik M.J. Bit by bit: Social research in the digital age. Princeton: Princeton University Press, 2019, 448 p.Vakhshtayn, V. Technics, or the Charm of Progress. St. Petersburg: European University press, 2021, 156 p. (In Russ.).Vakhshtayn, V. Technics, or the Charm of Progress. St. Petersburg: European University press, 2021, 156 p. (In Russ.).Wagschal U. Ettensperger F. Big Data in Social Sciences. In: Berg-Schlosser D., Badie B., Morlino L. (eds.) The SAGE Handbook of Political Science. London: SAGE Publications Ltd, 2020, P. 272–287. DOI: 10.4135/9781529714333.n19Wagschal U. Ettensperger F. Big Data in Social Sciences. In: Berg-Schlosser D., Badie B., Morlino L. (eds.) The SAGE Handbook of Political Science. London: SAGE Publications Ltd, 2020, P. 272–287. DOI: 10.4135/9781529714333.n19

The authors declare that there are no conflicts of interest present.