RUDN Journal of Political ScienceRUDN Journal of Political ScienceВестник Российского университета дружбы народов. Серия: Политология2313-14382313-1446Peoples’ Friendship University of Russia named after Patrice Lumumba (RUDN University)2428810.22363/2313-1438-2020-22-3-517-532MIGRATION AND POLITICAL TRANSFORMATIONS IN EUROPEМИГРАЦИЯ И ПОЛИТИЧЕСКИЕ ТРАНСФОРМАЦИИ В ЕВРОПЕResearch ArticleNatural Language Processing for the Analysis of the Political Characterisation of Migration in the Croatian Political DiscourseОбработка естественного языка для анализа политического определения миграции в хорватском политическом дискурсеDe LucaGabrieleДе ЛукаГабриэлеPhD Student of the Department of Comparative Politicsаспирант кафедры сравнительной политологииgabriele.deluca@mail.ruBeckMarkoБекМаркоPhD Student of the Department of Comparative Politicsаспирант кафедры сравнительной политологииbeck.marko@gmail.comPeoples’ Friendship University of Russia (RUDN University)Российский университет дружбы народов15122020223VOL 22, NO3 (2020)ТОМ 22, №3 (2020)51753201082020Copyright ©; 2020, De Luca G., Beck M.Copyright ©; 2020, Де Лука Г., Бек М.2020De Luca G., Beck M.Де Лука Г., Бек М.http://creativecommons.org/licenses/by/4.0https://journals.rudn.ru/political-science/article/view/24288This paper tackles the issue of analyst bias in performance of comparative political analyses on political discourse, by leveraging data and machine-learning over human prior knowledge. The case studied is characterization of the issue of migration in the Croatian political discourse, which was chosen arbitrarily. We developed a machine-learning system that identifies most prominent features in the Croatian political discourse, with regards to migration and were interested solo in comparative political analysis in political science. This system does not rely on human judgement on the part of the researchers, and can be thus considered to be “objective”, short of possible sampling or selection bias. It is replicable. If provided, the same dataset and algorithm used, same conclusions should be reached by any scientist. This result was achieved by creating a text corpus from news items and press releases extracted from the websites of Croatian political parties currently represented in the Parliament. Available and collected data consist of public announcements mainly from IDS (Istarski Demokratski Sabor / Istrian Democratic Assambly), SDSS (Samostalna Demokratska Srpska Stranka / Independed Democratic Serb Party) and HSLS (Hrvatska Socijalno Liberalna Stranka / Croatian Social Liberal Party). Data analyzed suggests three dominant phrases of the research process. All political parties had similar political stand towards pointed out issues. Three most significant phrases were determined. First phrase is related to words “Demography” and “Reduction” and finding suggest that most analyzed articles relates towards migration of Croatian citizens in connection to economic hardships of some kind. Phrase two is related to words “Border” and “Croatia-Serbia” which strongly indicates relation to migration and is related towards inter-Balkan migration, mostly connected with consequences of the Croatian War of Independence from 1990’s, and is of most interest to SDSS, a Serb minority party in Croatia. Phrase three is related towards Marrakesh Agreement (Global Compact for Safe, Orderly and Regular Migration), where most of analyzed data shows that parties have a constructive but ambivalent stance towards migration from the third countries. Research conducted on available data, shows that wide spread international migration is not in the focus of most Croatian political parties, while topics and interest for inter-Balkan and Croatian economic/political migration dominates Croatian political spectreСтатья посвящена решению проблемы предвзятости аналитиков при проведении сравнительного анализа политического дискурса. Предлагаемое решение строится на анализе данных и использовании машинного обучения для обработки естественного языка. Кейс, который мы изучаем в связи с этой проблемой, относится к определению проблемы миграции в хорватском политическом дискурсе. Была разработана система машинного обучения, которая выявляет наиболее характерные черты хорватского политического дискурса в отношении миграции: эта система свободна от исследовательской субъективности. Исследование воспроизводимо, и при условии, что используется тот же набор данных и алгоритм, любой ученый должен прийти к тем же выводам. Этот результат был достигнут на основе сбора корпус-текстов из новостных материалов и пресс-релизов с веб-сайтов хорватских политических партий, представленных в парламенте, а также группу алгоритмов классификации машинного обучения для матриц Bag-of-Words, вычисленных из корпуса. Мы определили наиболее точную модель, классификатор дерева решений, которая была выбрана для дальнейшего анализа из-за ее точности и интерпретируемости. Нами также проанализированы правила принятия решений, определенные этим классификатором, которые затем были интерпретированы людьми, чтобы определить политические особенности текста, которые лучше всего предсказывают связь этого текста с темой миграции. В итоге подробно раскрыты три правила, идентифицированные с этой процедурой, которые мы считаем особенно интересными.political discoursepublic information campaignmachine learninginformation retrievalnatural language processingmigrationполитический дискурскампания общественной информациимашинное обучениепоиск информацииобработка естественного языкамиграция1.Geddes B. How the cases you choose affect the answers you get: Selection bias in comparative politics. Political analysis. 1990; (2): 131-150.2.Pittman J.A., Yang Zh., Yu S. Political Cycles and Analyst Bias. 2018. doi: 10.2139/ssrn.32620703.Olsen M., Harvey L.G. Computers in intellectual history: lexical statistics and the analysis of political discourse. The Journal of Interdisciplinary History. 1988; 18 (3): 449-464.4.Gavrilova M.V. Political discourse as object of linguistic analysis. Polis. Political Studies. 2004; 3 (3): 127-139.5.Van Dijk T.A. What is political discourse analysis. Belgian journal of linguistics. 1997; 11 (1): 11-52.6.Collobert R., Weston J., Bottou L., Karlen M., Kavukcuoglu K., Kuksa P. Natural language processing (almost) from scratch. Journal of machine learning research. 2011; 12: 2493-2537.7.Bebić D. The role of the Internet in political communication and promoting political participation of citizens in Croatia: Internet election campaign 2007. Media Studies. 2011; 2: 3-4. (In Croat.).8.Ostojic R. A European Perspective of the Migration Crisis: Russian Experiences. Zagreb: Friedrich Ebert Foundation; 2016. (In Croat.).9.Sharich T. Escape from socialist Yugoslavia-illegal emigration from Croatia since 1945. by the early sixties of the 20th century. Migration and ethnic themes. 2015; (2): 195-220. (In Croat.).10.Žižić J. What is political emigration in Croatia? Political analysis. 2013; 4 (16): 61-64. (In Croat.).11.Sundhaussen H. Forced ethnic migration. Institut für Europäische Geschichte; 2010.12.Felberg T.R., Šarić L. In transit: Representations of migration on the Balkan route. Discourse analysis of Croatian and Serbian public broadcasters (RTS and HRT online). Journal of Language Aggression and Conflict. 2017; 5 (2): 227-250.13.Vezovnik A., Šarić L. Subjectless images: visualization of migrants in Croatian and Slovenian public broadcasters’ online news. Social Semiotics. 2020. 30 (2): 168-190.14.Šaric L., Felberg T.R. Representations of the 2015/2016 “migrant crisis” on the online portals of Croatian and Serbian public broadcasters. Migration and Media: Discourses about identities in crisis. 2019; 81: 203.15.Ragazzi F., Balalovska K. Diaspora politics and post-territorial citizenship in Croatia, Serbia and Macedonia. CITSEE Working Paper Series. 2011; 18.16.Ragazzi F. The Croatian ‘diaspora politics’ of the 1990s: nationalism unbound? Croatian ‘Diaspora Politics’ of the 1990s: Nationalism Unbound? In: U. Brunnbauer (ed.). Transnational Societies, Transterritorial Politics: Migrations in the (Post-) Yugoslav Region, 19th-21st Century. 2009.17.Knezović S., Grošinić M. Migration trends in Croatia. Zagreb: Hanns-Seidel-Stviftung, Institute of development and international relations, Kolor Klinika; 2017: 1-39.18.Rovny J. The other “other”: Party responses to immigration in Eastern Europe. Comparative European Politics. 2014; 12 (6): 637-662. doi: 10.1057/cep.2014.2519.Gregurović M., Kuti S., Župarić-Iljić D. Attitudes towards immigrant workers and asylum seekers in eastern Croatia: dimensions, determinants and differences. Migration and ethnic themes. 2016; 32 (1): 91-122.20.Nadkarni P. M., Ohno-Machado L., Chapman W.W. Natural language processing: an introduction. Journal of the American Medical Informatics Association. 2011; 18 (5): 544-551.21.Ljubešić N., Boras D., Kubelka O. Retrieving information in Croatian: Building a simple and efficient rule-based stemmer. 2007.22.Lipton Z.C., Elkan C., Naryanaswamy B. Optimal thresholding of classifiers to maximize F1 measure. Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin: Springer; 2014: 225-239.23.Assembly U.G. Global Compact for Safe, Orderly and Regular Migration. International Journal of Refugee Law. 2018; 30 (4): 774-816.