Issues of social protection and social security have always been among the most urgent for all, without exception, social strata. In the conditions of the war, this sphere acquired special importance. After all, the effectiveness of the state policy of social protection and social security depends not only on the well-being of citizens and the balanced development of society, but also on ensuring national security. During the war, the amount of spending on social protection and social security increased significantly and will continue to increase, despite the limited budgetary funding. Therefore, special attention needs to be paid to the targeting of funds for social protection and social security, as well as control over the targeting of state assistance. In the conditions of war, conducting sociological research, surveys, and personal reception of citizens becomes much more difficult. Taking into account the fact that a significant number of the population uses various social networks, digital platforms of state institutions and organizations, etc., the research of the online environment becomes a promising direction of work with citizens' appeals. Therefore, having information from Internet sources, it is possible to investigate problems that are significant for different social groups, to analyze the moods and expectations of the population. But at present, there are practically no software products in the social security system designed to analyze textual information presented in citizens' appeals. 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.
modern
models, methods and information technology. The introduction of the "Unified Information System of the Social Sphere" [17] was a new step towards the end-to-end digitalization of the pension system and social protection of the population. The purpose of the introduction of the System is to "ensure integral automation of processes in the social 8th International Scientific and Practical Conference Applied Information Systems and Technologies in the Digital Society AISTDS’2024, 2024, October 1, Kyiv, Ukraine * Corresponding author. sphere by optimizing and developing electronic information interaction of the subjects of the Unified System aimed at ensuring transparency of the social sphere, digitalization of the social support market and increasing the level of its availability for persons who need it" [17 ].
The development of the Unified Information System of the Social Sphere [
Therefore, the issue of developing methods, models, information technologies for the analysis of textual information from citizens' electronic appeals to institutions of social protection and social security, Internet sources, identifying issues that are most important for those who need state support, is urgent and of practical importance. [18-20].
The paper proposes a method of using text analytics tools to build an analytical model for the classification of text information in the task of analyzing citizens' appeals to the Pension Fund of Ukraine.
In the course of the study, the practical task of determining the need for social protection and social security of residents of different regions of Ukraine and refugees was considered. SAS Text Miner tools [21-23] were used to analyze text information.
Incoming information is electronic appeals from citizens that have arrived at the web portal of
electronic services of the Pension Fund of Ukraine and the state institution "Government Contact
Center [
Based on the analysis of texts related to issues of social protection and social security posted on the specified Internet resources and in electronic applications, six clusters were obtained.
The first cluster includes texts that contain issues related to the pension reform. The most characteristic words and phrases for this cluster were: "reform", "insurance payments", "insurance experience", "mandatory pension savings".
The second cluster includes words and phrases describing the issue of accrual and payment of pensions and social benefits by the Pension Fund of Ukraine: "timely payment of pensions", "voluntary contributions to pension insurance", "minimum pension", "indexation of pensions", "increase of pensions", "housing subsidy", "financing of current payments", "recalculation of pensions for working pensioners".
The third cluster summarizes the problems of social protection of internally displaced persons. The most characteristic are such words and phrases as "IDPs", "identification", "liberated territories", "payments to displaced persons", "inhabitants of the occupied Crimea", "UN World Food Program", "temporarily uncontrolled territories".
The fourth cluster includes words and phrases describing problems related to losses due to military conflict: "military serviceman", "policeman", "combat zone", "missing person", "loss of breadwinner", "family members of the deceased" ".
For the fifth cluster, the issues of social protection and social security of refugees are "relevant", in particular, "pension abroad", "work outside Ukraine", "proportional calculation of insurance experience", "insurance experience received in other countries".
The sixth cluster summarizes issues related to the victims of the accident at the Chernobyl NPP: "accident", "ChNPP", "Chernobyl".
Based on the preliminary analysis of the texts of the appeals, a corpus of texts was formed, a fragment of which is given in the table. 2.
To solve the problem of reducing the dimensionality and sparsity of the frequency matrix of the
corpus of texts, the method of singular distribution (SVD) was used [
On the basis of the obtained matrix S, it is possible to calculate the amount in percent that the corresponding dimension, which is described by the corresponding singular value, contributes to the explanation of the data (table 3). The value of the column "Percentage of value contribution to the explanation of data variability" is calculated as the value of "Square of the singular value" divided by the sum of the values of the squares of the singular values, multiplied by 100%.
As can be seen from the obtained results, table 3, if only the two basic dimensions are left, a total of 66.16% of the data variability will be explained.
In this case, all documents can be located in two -dimensional space and determine the clusters that they form according to the degree of similarity and belonging to a certain topic (Fig. 1).
As can be seen from fig. 1, the first dimension explains 45.61% of the data variability; the second
dimension explains 20.55% of the data variability. As a result, three thematic clusters were formed,
which included documents based on the similarity of the use of terms [
The SAS Text Miner system was used in this study. When using the SAS Text Miner software, a technological project is built in which the following steps are performed:
The technological process of analyzing the corpus of texts for the purpose of their clustering is presented in fig. 2.
The constructed rules for the corresponding clusters are generated in the form of the following program code:
F_TextCluster_cluster_ =1 :: (OR , "reform" , "insurance" , (AND, (OR, "payments", "seniority") ) , "accumulation" , (AND, (OR, "pensionable", "mandatory") ) F_TextCluster_cluster_ =2 :: , (AND, (OR, "payments" , "pension")) (OR , "voluntary" , "timely" , "pension" , (AND, (OR, "contributions" , "pension" , "insurance", "recalculation")) , (AND, (OR, "minimum" , "index" , "increment")) , "subsidy" , (AND, (OR, "residential")) , "current" , (AND, (OR, "payment" , "funding")) F_TextCluster_cluster_ =5 :: (OR , "pension" , (AND, (OR, "border", "borders", "others", "countries")) , "experience" , (AND, (OR, "calculation" , "insurance" , "proportional")) F_TextCluster_cluster_ =6 :: (OR , "accident" , (AND, (OR, "CHAES" , "nuclear" , "power plant")) , "Chernobyl"))))
The statistical characteristics of the built classification model based on linguistic rules were calculated separately for the training and test data sets: the ratio is 70% for training and 30% for testing, i.e. 114 and 48 texts, respectively.
The results are summarized in Table 3. Statistical characteristics of the classification model of the studied texts
The image of the ROC curve for the text information classification model based on linguistic rules
Statistics
TN (True Negative) FP (false positive) FN (false negative) MISC,% (proportion of incorrectly classified values) Ginny
ROC is presented in Fig. 3.
training 30 67 10 7 15 0.82 the model on the training set ROCcharacteristics of the model on the test set The reference line is 50 for 50 percent of the occurrence of the event
The constructed linguistic rules were used to cluster news texts that were published on the Internet from September 2023 to September 2024. In general, about 10,000 tons were unloaded and processed. texts on social protection and social security of Ukrainians.
After clustering the texts, the number of texts belonging to contributors from a certain region was calculated for each cluster. The obtained values were normalized on a scale from 0 to 100 according to formula (1): =
max( |∀ )
The results of the calculations are presented in Table 4. – the number of texts by region, max( |∀ ) – maximum number texts by all regions. where
– the popularity of the texts of the corresponding cluster for the i-th region,
Popularity of the texts of the corresponding cluster
of Vinnytsia region Volyn region the city of Kyiv the city Sevastopol Dnipropetrovsk region Donetsk region Zhytomyr region Transcarpathian region Zaporizhzhia region Ivano-Frankivsk region Kyiv region Kirovohrad region Autonomous Republic of Crimea Luhansk region Lviv region Mykolayiv region Odesa region Poltava region Rivne region Sumy region Ternopil region Kharkiv region Kherson region Khmelnytskyi region Cherkasy region Chernihiv region Chernivtsi region
Cluster 1 (pension reform) 94 87 82 58 27 94 67 58 87 84 92
The results of the analysis presented in the table can be visualized using SAS tools Enterprise Guide 7.1 (fig. 4-9).
The authors have not employed any Generative AI tools.
The proposed method of textual information analysis using text tools mining designed for automated processing of large volumes of texts on a certaintopic. The use of text analytics allows you to deepen your knowledge of the subject area by using unstructured data. In this study, the problem of dimensionality and sparsity of the frequency matrix of the corpus of texts is solved using the key theorem of linear algebra - the singular matrix decomposition (SVD) method. Pre-executed. frequency weighting operation, which helped to partially solve the problem of unevenness of highfrequency terms, making them less influential. This made it possible to obtain results of classification of textual information of high quality.
Therefore, the use of intellectual analysis of large volumes of textual data allows to identify the most important problems that require a priority solution, to find out for which categories of the population they are most relevant. The obtained results can be further used during the planning of social expenditures of budgets of different levels, in the model of actuarial calculations, during the planning of social expenditures of budgets of various levels. The proposed approach can improve the quality of forecasts in modern conditions, when there is no complete information about the investigated process or phenomenon or the information is distorted. [14] Text Cluster Node Results. URL: https://documentation.sas.com/?docsetId=tmref&docsetTarget=n1d7r58qug6sefn162cu6cqx0nq 4.htm&docsetVersion=14.3&locale=en [15] Emerging Technologies of Text Mining: Techniques and Applications / Ed. by HA Do Prado, E.
Ferneda. Idea Group Reference, 2007. 358 p. [16] Valls Martínez, MdC, Santos-Jaén, JM, Amin, F.-u., Martín-Cervantes, PA Pensions, Aging and Social Security Research: Literature Review and Global Trends. Mathematics 2021, No. 9, 3258. https://doi.org/10.3390/math9243258 [17] Social Protection Systems. Ed. E. Schüring, M. Loewe. Elgar Publishing. 2021. 776 p.
https://doi.org/10.4337/9781839109119 [18] Official website of the Ministry of Digital Transformation of Ukraine. URL : https://thedigital.gov.ua (ukr) [19] On the approval of the Regulation on the Unified Information System of the Social Sphere.
Resolution of the Cabinet of Ministers of Ukraine dated April 14, 2021 No. 404. URL : https://zakon.rada.gov.ua/laws/show/404-2021-п#Text (ukr) [20] Gladun A. Ya., Rogushina Yu. IN. Data mining : searching for knowledge in data: a tutorial. Kyiv:
ADEF-Ukraine, 2016. 451 p. (ukr) [21] Lytvyn V.V., Pasichnyk V.V., Nikolskyi Yu.V. Analysis of data and knowledge: training. manual
Lviv: Magnolia 2006, 2017. 276 p. (ukr) [22] Analysis and processing of data flows by means of computational intelligence: monograph / Ye.
IN. Bodyanskyi et al. Lviv: View of Lviv. polytechnics, 2016. 235 p. (ukr) [23] Text analytics using SAS Text Miner: course notes. NC.: SAS Institute, 2014. 218 p. [24] Getting Started with SAS® Text Miner 12.1 URL: https://support.sas.com/documentation/onlinedoc/txtminer/12.1/tmgs.pdf [25] Matignon R. Data Mining Using SAS Enterprise Miner. URL: https://www.amazon.com/Data
Mining-Using-Enterprise-Miner/dp/0470149019 [26] Sharma S., JainRole A. Role of sentiment analysis in social media security and analytics. WIREs
Data Mining and Knowledge Discovery: Vol. 10, Issue 5. https://doi.org/10.1002/widm.1366 [27] Find the information that matters using natural language processing (NLP). URL: https://www.sas.com/ru_ua/software/visual-text-analytics.html