МЕТОДИКА ЗАСТОСУВАННЯ КЛАСТЕРИЗАЦІЇ ТЕКСТІВ НА ОСНОВІ ЛІНГВІСТИЧНИХ ПРАВИЛ ДЛЯ ДОСЛІДЖЕННЯ ПОТРЕБ НАСЕЛЕННЯ У СОЦІАЛЬНОМУ ЗАХИСТІ ТА СОЦІАЛЬНОМУ ЗАБЕЗПЕЧЕННІ

Юзеф КОРБИЧ; Олексій ШОЛОХОВ; Олексій ЗАРУДНИЙ; Роман КОВАЛЬ

doi:10.17721/3041-2323.2024.172-184

Authors

Józef KORBICZ University of Zielona Góra Author
Oleksii SHOLOKHOV Taras Shevchenko National University of Kyiv Author
Oleksii ZARUDNYI Institute of Telecommunications and Global Information Space of the National Academy of Sciences of Ukraine Author
Roman KOVAL Institute of Telecommunications and Global Information Space of the National Academy of Sciences of Ukraine Author

DOI:

https://doi.org/10.17721/3041-2323.2024.172-184

Keywords:

text clustering, linguistic rules, intelligent data analysis, social protection and social security, information technology

Abstract

Issues of social protection and social security have always been among the most pressing for all segments of society without exception. In times of war, this sphere has acquired special significance, as the effectiveness of state policy in social protection and social security determines not only the well-being of citizens and balanced societal development but also the safeguarding of national security. During the war, expenditures on social protection and social security have increased significantly and are expected to continue growing, despite limited budgetary. Therefore, special attention must be paid to the targeted allocation of funds for social protection and social security, as well as to the control of the proper targeting of state aid Since conducting sociological research during wartime is significantly complicated, exploring the online environment becomes a promising direction. A large portion of the population uses various social networks, digital platforms of state institutions and organizations, and more. Hence, by analyzing information from internet sources, it is possible to investigate issues relevant to different social groups, as well as assess the sentiments and expectations of the population (Sharma & JainRole, n. d.; Shkurko, 2018; Perebyinis, 2013; Lande, 2014; Find the information that matters using natural language processing (NLP), n. d.; Berry, 2003; Aggarwal, n. d.; Text Cluster Node Results, n. d.; Do Prado & Ferneda, 2007).The work proposes a method of building an analytical model for the study of social protection and social security problems that require special attention from the state, using means of analyzing textual information from Internet sources and building classification models.

References

Aggarwal, C. C., & Zhai, C. (2012). Mining text data. Springer.

Berry, M. W. (Ed.). (2003). Survey of text mining I: Clustering, classification, and retrieval. Springer.

Bodianskyi, Y. V. (2016). Analysis and processing of data streams using computational intelligence. Lviv Polytechnic Publishing [in Ukrainian].

Do Prado, H. A., & Ferneda, E. (Eds.). (2007). Emerging technologies of text mining: Techniques and applications. Idea Group Reference. Find the information that matters using natural language processing (NLP). (n. d.). https://www.sas.com/ru_ua/software/visual-text-analytics.html.

Gladun, A. Y., & Rogushina, Y. V. (2016). Data mining: Search for knowledge in data.. ADEF-Ukraine [in Ukrainian].

Gren, T. Y. (2022). Features of implementing social protection policy in wartime conditions. Scientific Notes of TNU named after V. I. Vernadsky. Series: Public Administration and Governance, 33(72), 6, 81–84 [in Ukrainian]. https://doi.org/10.32782/TNU-2663-6468/2022.6/13

Lande, D. V. (2014). Elements of computational linguistics in legal informatics. Kyiv: Research Institute of Legal Informatics [in Ukrainian].

Litvin, V. V., Pasichnyk, V. V., & Nikolskyi, Y. V. (2017). Data and knowledge analysis: Textbook. Magnolia 2006 [in Ukrainian].

Matignon, R. (2007). Data mining using SAS Enterprise Miner. https://www.amazon.com/Data-Mining-Using-Enterprise-Miner/dp/0470149019.

Ministry of Digital Transformation of Ukraine. (n. d.). Official website of the Ministry of Digital Transformation of Ukraine [in Ukrainian]. https://thedigital.gov.ua

Ministry of Finance of Ukraine. (n. d.). Expenditures on social assistance [in Ukrainian]. https://mof.gov.ua/uk/expenditures_on_social_assistance

Perebyinis, V. I. (2013). Statistical methods for linguists. Nova Knyha [in Ukrainian].

Schüring, E., & Loewe, M. (Eds.). (2021). Social protection systems. Edward Elgar Publishing. https://doi.org/10.4337/9781839109119.

Sharma, S., & Jain, A. (n. d.). Role of sentiment analysis in social media security and analytics. WIREs Data Mining and Knowledge Discovery, 10(5). https://doi.org/10.1002/widm.1366.

Shapovalova, T. (2022). Concept and content of social protection and social security of the population in modern Ukraine. Economic Analysis, 32(3), 123–130 [in Ukrainian]. https://doi.org/10.35774/econa2022.03.123

Shkurko, O. V. (2018). Types of linguistic text analysis. Dnipro: Alfred Nobel University [in Ukrainian].

Smush-Kulesha, M., Fedorova, A., & Moisa, B. (2022). Social rights in Ukraine during the war. Needs assessment report. Council of Europe [in Ukrainian]. https://rm.coe.int/needs-assessment-ua-2/1680a9b408

SAS Institute. (2012). Getting started with SAS® Text Miner 12.1. https://support.sas.com/documentation/onlinedoc/txtminer/12.1/tmgs.pdf.

SAS Institute. (2014). Text analytics using SAS Text Miner: Course notes. https://documentation.sas.com/?docsetId=tmref&docsetTarget=n1d7r58qug6sefn162cu6cqx0nq4.htm&docsetVersion=14.3&locale=en

Text Cluster Node Results. (n. d.). https://documentation.sas.com/?docsetId=tmref-

&docsetTarget=n1d7r58qug6sefn162cu6cqx0nq4.htm&docsetVersion=14.3&locale=en.

Valls Martínez, M. d. C., Santos-Jaén, J. M., Amin, F.-u., & Martín-Cervantes, P. A. (2021). Pensions, ageing and social security research: Literature review and global trends. Mathematics, 9, 3258. https://doi.org/10.3390/math9243258.