{"id":12497,"date":"2022-05-13T12:10:55","date_gmt":"2022-05-13T09:10:55","guid":{"rendered":"http:\/\/journals.khnu.km.ua\/vestnik\/?p=12497"},"modified":"2022-06-07T01:26:22","modified_gmt":"2022-06-06T22:26:22","slug":"methods-of-classification-of-machine-learning-for-construction-of-mathematical-models-on-multimodal-data","status":"publish","type":"post","link":"https:\/\/journals.khnu.km.ua\/vestnik\/?p=12497","title":{"rendered":"Methods of classification of machine learning for construction of mathematical models on multimodal DATA"},"content":{"rendered":"

<\/p>\n

METHODS OF CLASSIFICATION OF MACHINE LEARNING FOR CONSTRUCTION OF MATHEMATICAL MODELS ON MULTIMODAL DATA<\/p>\n

\u041c\u0415\u0422\u041e\u0414\u0418 \u041a\u041b\u0410\u0421\u0418\u0424\u0406\u041a\u0410\u0426\u0406\u0407 \u041c\u0410\u0428\u0418\u041d\u041d\u041e\u0413\u041e \u041d\u0410\u0412\u0427\u0410\u041d\u041d\u042f \u0414\u041b\u042f \u041f\u041e\u0411\u0423\u0414\u041e\u0412\u0418 \u041c\u0410\u0422\u0415\u041c\u0410\u0422\u0418\u0427\u041d\u0418\u0425 \u041c\u041e\u0414\u0415\u041b\u0415\u0419 \u041d\u0410 \u041c\u0423\u041b\u042c\u0422\u0418\u041c\u041e\u0414\u0410\u041b\u042c\u041d\u0418\u0425 \u0414\u0410\u041d\u0418\u0425<\/p>\n

\u0421\u0442\u043e\u0440\u0456\u043d\u043a\u0438:\u00a02<\/strong>5<\/strong>-3<\/strong>2<\/strong>. \u041d\u043e\u043c\u0435\u0440: \u21162, 2022 (307) \"\"<\/a> <\/strong>
\n\u00a0\u0410\u0432\u0442\u043e\u0440\u0438:<\/strong>
\nBOYKO N.\u0406.
\nLviv Polytechnic National University
\nORCID ID: 0000-0002-6962-9363<\/a>
\ne-mail: Nataliya.i.boyko@lpnu.ua<\/a>
\nPETROVSKYI O.S.
\nLviv Polytechnic National University
\nORCID ID: 0000-0002-5729-544X<\/a>
\ne-mail: oleksandr.petrovskyi.knm.2018@lpnu.ua<\/a>
\n\u0411\u043e\u0439\u043a\u043e \u041d.\u0406., \u041f\u0435\u0442\u0440\u043e\u0432\u0441\u044c\u043a\u0438\u0439 \u041e.\u0421.
\n\u041d\u0430\u0446\u0456\u043e\u043d\u0430\u043b\u044c\u043d\u0438\u0439 \u0443\u043d\u0456\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442 \u201c\u041b\u044c\u0432\u0456\u0432\u0441\u044c\u043a\u0430 \u043f\u043e\u043b\u0456\u0442\u0435\u0445\u043d\u0456\u043a\u0430\u201d<\/p>\n

\u00a0DOI:<\/strong>\u00a0https:\/\/www.doi.org\/10.31891\/2307-5732-2022-307-2-25-32<\/a><\/p>\n

\u0410\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u043c\u043e\u0432\u043e\u044e \u043e\u0440\u0438\u0433\u0456\u043d\u0430\u043b\u0443<\/strong><\/p>\n

This article is dedicated to topic modeling as an unsupervised machine learning technique. It is analyzed how it seems possible to determine the topics of documents in order to categorize them further with the help of topic modeling methods. Such methods as latent semantic analysis, probabilistic latent semantic analysis and latent Dirichlet allocation are considered. An approach that allows the construction of effective topic models of text document collections in Ukrainian and other synthetic languages based on peculiarities of this linguistic language type is proposed, and its main stages are described. The proposed approach consists of a custom input data preprocessing pipeline, which covers file loading, text extraction, removal of improper symbols, tokenization, removal of stop-words, stemming of each token and a newly introduced model pruning stage, which makes any of the modern topic modeling methods applicable for synthetic language topic modeling. The approach was implemented in Python programming language and used to obtain the topic model of the collection of Ukrainian-language scientific publications on civic identity and related topics. An expert in political psychology, who studies the phenomenon of civic identity, was involved in the research for the topic model quality evaluation. As a result of expert evaluation of the topics singled out during the modeling, it was proposed to clarify the formulation of cluster names based on the semantics of the sets of words that form them. In general, according to the expert, the topics singled out represent the concept of the civic identity of an individual and will allow researchers to simplify the work with literature sources on this issue when used to categorize documents. This demonstrates the efficiency of the proposed approach.
\nKeywords:<\/strong> topic modeling, natural language processing, text preprocessing, latent Dirichlet allocation, latent semantic analysis, pachinko allocation, synthetic language.
\n\u00a0<\/strong><\/p>\n

\u00a0\u0420\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u0430 \u0430\u043d\u043e\u0442\u0430\u0446\u0456\u044f <\/strong><\/p>\n

\u0421\u0442\u0430\u0442\u0442\u044f \u043f\u0440\u0438\u0441\u0432\u044f\u0447\u0435\u043d\u0430 \u0442\u0435\u043c\u0430\u0442\u0438\u0447\u043d\u043e\u043c\u0443 \u043c\u043e\u0434\u0435\u043b\u044e\u0432\u0430\u043d\u043d\u044e \u044f\u043a \u0442\u0435\u0445\u043d\u0456\u0446\u0456 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f \u0431\u0435\u0437 \u0432\u0447\u0438\u0442\u0435\u043b\u044f. \u0410\u043d\u0430\u043b\u0456\u0437\u0443\u0454\u0442\u044c\u0441\u044f \u043c\u043e\u0436\u043b\u0438\u0432\u0456\u0441\u0442\u044c \u0432\u0438\u0437\u043d\u0430\u0447\u0435\u043d\u043d\u044f \u0442\u0435\u043c \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u0438\u0445 \u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u0456\u0432 \u043c\u0435\u0442\u043e\u0434\u0430\u043c\u0438 \u0442\u0435\u043c\u0430\u0442\u0438\u0447\u043d\u043e\u0433\u043e \u043c\u043e\u0434\u0435\u043b\u044e\u0432\u0430\u043d\u043d\u044f \u0437 \u043c\u0435\u0442\u043e\u044e \u0457\u0445 \u043f\u043e\u0434\u0430\u043b\u044c\u0448\u043e\u0457 \u043a\u0430\u0442\u0435\u0433\u043e\u0440\u0438\u0437\u0430\u0446\u0456\u0457. \u0420\u043e\u0437\u0433\u043b\u044f\u0434\u0430\u044e\u0442\u044c\u0441\u044f \u0442\u0430\u043a\u0456 \u043c\u0435\u0442\u043e\u0434\u0438, \u044f\u043a \u043b\u0430\u0442\u0435\u043d\u0442\u043d\u043e-\u0441\u0435\u043c\u0430\u043d\u0442\u0438\u0447\u043d\u0438\u0439 \u0430\u043d\u0430\u043b\u0456\u0437, \u0439\u043c\u043e\u0432\u0456\u0440\u043d\u0456\u0441\u043d\u0438\u0439 \u043b\u0430\u0442\u0435\u043d\u0442\u043d\u043e-\u0441\u0435\u043c\u0430\u043d\u0442\u0438\u0447\u043d\u0438\u0439 \u0430\u043d\u0430\u043b\u0456\u0437 \u0442\u0430 \u043b\u0430\u0442\u0435\u043d\u0442\u043d\u0435 \u0440\u043e\u0437\u043c\u0456\u0449\u0435\u043d\u043d\u044f \u0414\u0456\u0440\u0456\u0445\u043b\u0435. \u0417\u0430\u043f\u0440\u043e\u043f\u043e\u043d\u043e\u0432\u0430\u043d\u043e \u043f\u0456\u0434\u0445\u0456\u0434, \u044f\u043a\u0438\u0439 \u0440\u043e\u0431\u0438\u0442\u044c \u043c\u043e\u0436\u043b\u0438\u0432\u0438\u043c \u0435\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u0443 \u043f\u043e\u0431\u0443\u0434\u043e\u0432\u0443 \u0442\u0435\u043c\u0430\u0442\u0438\u0447\u043d\u0438\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u043a\u043e\u043b\u0435\u043a\u0446\u0456\u0439 \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u0438\u0445 \u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u0456\u0432 \u0443\u043a\u0440\u0430\u0457\u043d\u0441\u044c\u043a\u043e\u044e \u0442\u0430 \u0456\u043d\u0448\u0438\u043c\u0438 \u0441\u0438\u043d\u0442\u0435\u0442\u0438\u0447\u043d\u0438\u043c\u0438 \u043c\u043e\u0432\u0430\u043c\u0438, \u0437\u0430\u0441\u043d\u043e\u0432\u0430\u043d\u0438\u0439 \u043d\u0430 \u043e\u0441\u043e\u0431\u043b\u0438\u0432\u043e\u0441\u0442\u044f\u0445 \u043c\u043e\u0432 \u0446\u044c\u043e\u0433\u043e \u043b\u0456\u043d\u0433\u0432\u0456\u0441\u0442\u0438\u0447\u043d\u043e\u0433\u043e \u0442\u0438\u043f\u0443, \u0442\u0430 \u043e\u043f\u0438\u0441\u0430\u043d\u043e \u0439\u043e\u0433\u043e \u0433\u043e\u043b\u043e\u0432\u043d\u0456 \u0435\u0442\u0430\u043f\u0438. \u0410\u0432\u0442\u043e\u0440\u0441\u044c\u043a\u0438\u0439 \u043f\u0456\u0434\u0445\u0456\u0434 \u043f\u043e\u043b\u044f\u0433\u0430\u0454 \u0443 \u043e\u0441\u043e\u0431\u043b\u0438\u0432\u043e\u043c\u0443 \u043a\u043e\u043d\u0432\u0435\u0454\u0440\u0456 \u043f\u043e\u043f\u0435\u0440\u0435\u0434\u043d\u044c\u043e\u0457 \u043e\u0431\u0440\u043e\u0431\u043a\u0438 \u0432\u0445\u0456\u0434\u043d\u0438\u0445 \u0434\u0430\u043d\u0438\u0445, \u0449\u043e \u043e\u0445\u043e\u043f\u043b\u044e\u0454 \u0437\u0430\u0432\u0430\u043d\u0442\u0430\u0436\u0435\u043d\u043d\u044f \u0444\u0430\u0439\u043b\u0456\u0432, \u0432\u0438\u0434\u043e\u0431\u0443\u0432\u0430\u043d\u043d\u044f \u0442\u0435\u043a\u0441\u0442\u0443, \u0432\u0438\u0434\u0430\u043b\u0435\u043d\u043d\u044f \u0437\u0430\u0439\u0432\u0438\u0445 \u0441\u0438\u043c\u0432\u043e\u043b\u0456\u0432, \u0442\u043e\u043a\u0435\u043d\u0456\u0437\u0430\u0446\u0456\u044e, \u0432\u0438\u0434\u0430\u043b\u0435\u043d\u043d\u044f \u0441\u0442\u043e\u043f-\u0441\u043b\u0456\u0432, \u0441\u0442\u0435\u043c\u043c\u0456\u043d\u0433 \u043a\u043e\u0436\u043d\u043e\u0433\u043e \u0442\u043e\u043a\u0435\u043d\u0443, \u0456 \u043d\u043e\u0432\u043e\u0432\u0432\u0435\u0434\u0435\u043d\u0438\u0439 \u0435\u0442\u0430\u043f \u043f\u0440\u0443\u043d\u0456\u043d\u0433\u0443, \u0449\u043e \u0440\u0430\u0437\u043e\u043c \u0434\u043e\u0437\u0432\u043e\u043b\u044f\u0454 \u0437\u0430\u0441\u0442\u043e\u0441\u043e\u0432\u0443\u0432\u0430\u0442\u0438 \u0431\u0443\u0434\u044c-\u044f\u043a\u0456 \u0441\u0443\u0447\u0430\u0441\u043d\u0456 \u043c\u0435\u0442\u043e\u0434\u0438 \u0442\u0435\u043c\u0430\u0442\u0438\u0447\u043d\u043e\u0433\u043e \u043c\u043e\u0434\u0435\u043b\u044e\u0432\u0430\u043d\u043d\u044f \u0434\u043b\u044f \u043a\u043e\u043b\u0435\u043a\u0446\u0456\u0439 \u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u0456\u0432 \u0441\u0438\u043d\u0442\u0435\u0442\u0438\u0447\u043d\u0438\u043c\u0438 \u043c\u043e\u0432\u0430\u043c\u0438.\u00a0 \u041e\u043f\u0438\u0441\u0430\u043d\u0438\u0439 \u043f\u0456\u0434\u0445\u0456\u0434 \u0431\u0443\u0432 \u0440\u0435\u0430\u043b\u0456\u0437\u043e\u0432\u0430\u043d\u0438\u0439 \u043c\u043e\u0432\u043e\u044e Python \u0456 \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u0430\u043d\u0438\u0439 \u0434\u043b\u044f \u043f\u043e\u0431\u0443\u0434\u043e\u0432\u0438 \u0442\u0435\u043c\u0430\u0442\u0438\u0447\u043d\u043e\u0457 \u043c\u043e\u0434\u0435\u043b\u0456 \u043a\u043e\u043b\u0435\u043a\u0446\u0456\u0457 \u0443\u043a\u0440\u0430\u0457\u043d\u043e\u043c\u043e\u0432\u043d\u0438\u0445 \u043d\u0430\u0443\u043a\u043e\u0432\u0438\u0445 \u043f\u0443\u0431\u043b\u0456\u043a\u0430\u0446\u0456\u0439 \u0437 \u043f\u0440\u043e\u0431\u043b\u0435\u043c\u0430\u0442\u0438\u043a\u0438 \u0433\u0440\u043e\u043c\u0430\u0434\u044f\u043d\u0441\u044c\u043a\u043e\u0457 \u0456\u0434\u0435\u043d\u0442\u0438\u0447\u043d\u043e\u0441\u0442\u0456 \u0442\u0430 \u0441\u0443\u043c\u0456\u0436\u043d\u0438\u0445 \u0442\u0435\u043c. \u0415\u043a\u0441\u043f\u0435\u0440\u0442 \u0437 \u043f\u043e\u043b\u0456\u0442\u0438\u0447\u043d\u043e\u0457 \u043f\u0441\u0438\u0445\u043e\u043b\u043e\u0433\u0456\u0457, \u044f\u043a\u0438\u0439 \u0432\u0438\u0432\u0447\u0430\u0454 \u0444\u0435\u043d\u043e\u043c\u0435\u043d \u0433\u0440\u043e\u043c\u0430\u0434\u044f\u043d\u0441\u044c\u043a\u043e\u0457 \u0456\u0434\u0435\u043d\u0442\u0438\u0447\u043d\u043e\u0441\u0442\u0456, \u0431\u0443\u0432 \u0437\u0430\u043b\u0443\u0447\u0435\u043d\u0438\u0439 \u0434\u043e \u0434\u043e\u0441\u043b\u0456\u0434\u0436\u0435\u043d\u043d\u044f \u0437\u0430 \u0442\u0435\u043c\u043e\u044e \u043e\u0446\u0456\u043d\u043a\u0438 \u044f\u043a\u043e\u0441\u0442\u0456 \u043c\u043e\u0434\u0435\u043b\u0456. \u0423 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0456 \u0435\u043a\u0441\u043f\u0435\u0440\u0442\u043d\u043e\u0457 \u043e\u0446\u0456\u043d\u043a\u0438 \u0432\u0438\u0434\u0456\u043b\u0435\u043d\u0438\u0445 \u043f\u0456\u0434 \u0447\u0430\u0441 \u043f\u043e\u0431\u0443\u0434\u043e\u0432\u0438 \u043c\u043e\u0434\u0435\u043b\u0456 \u0442\u0435\u043c \u0431\u0443\u043b\u043e \u0437\u0430\u043f\u0440\u043e\u043f\u043e\u043d\u043e\u0432\u0430\u043d\u043e \u0443\u0442\u043e\u0447\u043d\u0438\u0442\u0438 \u0444\u043e\u0440\u043c\u0443\u043b\u044e\u0432\u0430\u043d\u043d\u044f \u043d\u0430\u0437\u0432 \u043a\u043b\u0430\u0441\u0442\u0435\u0440\u0456\u0432 \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0456 \u0441\u0435\u043c\u0430\u043d\u0442\u0438\u043a\u0438 \u043d\u0430\u0431\u043e\u0440\u0456\u0432 \u0441\u043b\u0456\u0432, \u0449\u043e \u0457\u0445 \u0443\u0442\u0432\u043e\u0440\u044e\u044e\u0442\u044c. \u0417\u0430\u0433\u0430\u043b\u043e\u043c, \u043d\u0430 \u0434\u0443\u043c\u043a\u0443 \u0435\u043a\u0441\u043f\u0435\u0440\u0442\u0430, \u0432\u0438\u0434\u0456\u043b\u0435\u043d\u0456 \u0442\u0435\u043c\u0438 \u0432\u0456\u0434\u043e\u0431\u0440\u0430\u0436\u0430\u044e\u0442\u044c \u043f\u043e\u043d\u044f\u0442\u0442\u044f \u0433\u0440\u043e\u043c\u0430\u0434\u044f\u043d\u0441\u044c\u043a\u043e\u0457 \u0456\u0434\u0435\u043d\u0442\u0438\u0447\u043d\u043e\u0441\u0442\u0456 \u043e\u0441\u043e\u0431\u0438\u0441\u0442\u043e\u0441\u0442\u0456 \u0442\u0430 \u0434\u043e\u0437\u0432\u043e\u043b\u044f\u0442\u044c \u0434\u043e\u0441\u043b\u0456\u0434\u043d\u0438\u043a\u0430\u043c \u0441\u043f\u0440\u043e\u0441\u0442\u0438\u0442\u0438 \u0440\u043e\u0431\u043e\u0442\u0443 \u0437 \u043b\u0456\u0442\u0435\u0440\u0430\u0442\u0443\u0440\u043d\u0438\u043c\u0438 \u0434\u0436\u0435\u0440\u0435\u043b\u0430\u043c\u0438 \u0437 \u0446\u044c\u043e\u0433\u043e \u043f\u0438\u0442\u0430\u043d\u043d\u044f \u043f\u0440\u0438 \u043a\u0430\u0442\u0435\u0433\u043e\u0440\u0438\u0437\u0430\u0446\u0456\u0457 \u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u0456\u0432. \u0426\u0435 \u0441\u0432\u0456\u0434\u0447\u0438\u0442\u044c \u043f\u0440\u043e \u0435\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u0456\u0441\u0442\u044c \u0437\u0430\u043f\u0440\u043e\u043f\u043e\u043d\u043e\u0432\u0430\u043d\u043e\u0433\u043e \u043f\u0456\u0434\u0445\u043e\u0434\u0443.
\n\u041a\u043b\u044e\u0447\u043e\u0432\u0456 \u0441\u043b\u043e\u0432\u0430:<\/strong> \u0442\u0435\u043c\u0430\u0442\u0438\u0447\u043d\u0435 \u043c\u043e\u0434\u0435\u043b\u044e\u0432\u0430\u043d\u043d\u044f, \u043e\u0431\u0440\u043e\u0431\u043a\u0430 \u043f\u0440\u0438\u0440\u043e\u0434\u043d\u0456\u0445 \u043c\u043e\u0432, \u043f\u043e\u043f\u0435\u0440\u0435\u0434\u043d\u044f \u043e\u0431\u0440\u043e\u0431\u043a\u0430 \u0442\u0435\u043a\u0441\u0442\u0443, \u043b\u0430\u0442\u0435\u043d\u0442\u043d\u0435 \u0440\u043e\u0437\u043c\u0456\u0449\u0435\u043d\u043d\u044f \u0414\u0456\u0440\u0456\u0445\u043b\u0435, \u043b\u0430\u0442\u0435\u043d\u0442\u043d\u043e-\u0441\u0435\u043c\u0430\u043d\u0442\u0438\u0447\u043d\u0438\u0439 \u0430\u043d\u0430\u043b\u0456\u0437, \u0440\u043e\u0437\u043c\u0456\u0449\u0435\u043d\u043d\u044f \u043f\u0430\u0447\u0456\u043d\u043a\u043e, \u0441\u0438\u043d\u0442\u0435\u0442\u0438\u0447\u043d\u0430 \u043c\u043e\u0432\u0430.<\/p>\n

References<\/strong><\/p>\n

    \n
  1. Tkalenko O. Intelligent technologies and artificial intelligence systems to support decision making \/ O. Tkalenko, A. Makarenko, O. Polonevych \/\/ Telecommunication and information technologies. \u2013 2019. \u2013 Vol. 2. \u2013 P. 53\u201359.<\/li>\n
  2. Daud A. Knowledge discovery through directed probabilistic topic models: a survey \/ A. Daud, J. Li, L. Zhou, et al. \/\/ Front. Comput. Sci. China. \u2013 2010. \u2013 Vol. 4. \u2013 280\u2013301.<\/li>\n
  3. Vorontsov K. Probabilistic topic modeling. \u2013 2013. URL:machinelearning.ru\/wiki\/images\/2\/22\/Voron-2013-ptm.pdf<\/li>\n
  4. Jain A. Data Clustering: A Review \/ A. Jain, M. Murty, P. Flynn \/\/ ACM Computing Surveys. \u2013 1999. \u2013 Vol. 31, No. 3. \u2013 P. 264\u2013323.<\/li>\n
  5. Vorontsov K. Regularization, robustness and sparsity of probabilistic topic models \/ K. Vorontsov, A. Potapenko \/\/ Computer Research and Modeling. \u2013 2012. \u2013 Vol. 4, No. 4. \u2013 P. 693\u2013706.<\/li>\n
  6. Argyrou A. Topic modelling on Instagram hashtags: An alternative way to Automatic Image Annotation? \/ A. Argyrou, S. Giannoulakis, N. Tsapatsoulis. \u2013 URL: https:\/\/ieeexplore.ieee.org\/abstract\/document\/8501887.<\/li>\n
  7. Kirill Y. Propaganda Identification Using Topic Modelling \/ Y. Kirill, I. Mihail, M. Sanzhar, M. Rustam, F. Olga, M. Ravil \/\/ Procedia Computer Science. \u2013 2020. \u2013 Vol. 178. \u2013 P. 205\u2013212.<\/li>\n
  8. Huang T. Automatic meeting summarization and topic detection system \/ T. Huang, C. Hsieh, H. Wang \/\/ Data Technologies and Applications. \u2013 2018. \u2013 Vol. 52, No. 3. \u2013 P.351\u2013365.<\/li>\n
  9. Venkatesh A. On Evaluating and Comparing Open Domain Dialog Systems \/ A.Venkatesh, C. Khatri, A. Ram, F. Guo, F., et al. \u2013 2018. URL: https:\/\/arxiv.org\/pdf\/1801.03625.pdf<\/li>\n
  10. Ma J. A Message Topic Model for Multi-Grain SMS Spam Filtering. \/ J. Ma, Y. Zhang, Z. Wang, K. Yu \/\/ International Journal of Technology and Human Interaction. \u2013 2016. \u2013 Vol. 12, No. 2. \u2013 P. 83\u201395.<\/li>\n
  11. Spina D. Learning similarity functions for topic detection in online reputation monitoring \/ D. Spina, J. Gonzalo, E. Amig\u00f3 \/\/ Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval. \u2013 2014. URL: https:\/\/dl.acm.org\/doi\/10.1145\/2600428.2609621<\/li>\n
  12. Tutubalina E. Exploring convolutional neural networks and topic models for user profiling from drug reviews \/ E. Tutubalina, S. Nikolenko \/\/ Multimedia Tools and Applications. \u2013 2017. https:\/\/doi.org\/10.1007\/s11042-017-5336-z<\/li>\n
  13. Peters N. Task Boundary Inference via Topic Modeling to Predict Interruption Timings for Human-Machine Teaming \/ N. Peters, G. Bradley, T. Marshall-Bradley \/\/ Advances in Intelligent Systems and Computing. \u2013 2019. \u2013 P. 783\u2013788.<\/li>\n
  14. Schneider N. Chemical Topic Modeling: Exploring Molecular Data Sets Using a Common Text-Mining Approach \/ N. Schneider, N. Fechner, G. Landrum, N. Stiefl \/\/ Journal of Chemical Information and Modeling. \u2013 2017. \u2013 Vol. 57, No. 8. \u2013 P. 1816\u20131831.<\/li>\n
  15. Asmussen C. Smart literature review: a practical topic modelling approach to exploratory literature review \/ C. Asmussen, C. M\u00f8ller \/\/ Journal of Big Data. \u2013 2019. \u2013 Vol. 6, No. 1. https:\/\/doi.org\/10.1186\/s40537-019-0255-7<\/li>\n
  16. Hofmann Probabilistic Latent Semantic Analysis \/ T. Hofmann. \u2013 1992. URL: https:\/\/www.iro.umontreal.ca\/~nie\/IFT6255\/Hofmann-UAI99.pdf<\/li>\n
  17. Blei D. Latent Dirichlet Allocation \/ D. Blei, M. Jordan \/\/ Journal of Machine Learning Research. \u2013 2003. \u2013 Vol. 3. \u2013 P. 993\u20131022.<\/li>\n
  18. G\u00fcnther E. Word Counts and Topic Models \/ E. G\u00fcnther, T. Quandt \/\/ Digital Journalism. \u2013 2016. \u2013 Vol. 4, No. 1. \u2013 P. 75\u201388.<\/li>\n
  19. Blei D. Correlated topic models \/ D. Blei, J. Lafferty \/\/Advances in neural information processing systems. \u2013 2006. \u2013 Vol. 18. URL: https:\/\/citeseerx.ist.psu.edu\/viewdoc\/download?doi=10.1.1.958.2484&rep=rep1&type=pdf<\/li>\n
  20. Li W. Nonparametric Bayes Pachinko Allocation \/ W. Li, D. Blei, A. McCallum. \u2013 2007. URL: https:\/\/arxiv.org\/ftp\/arxiv\/papers\/1206\/1206.5270.pdf<\/li>\n
  21. Petrovska I. Psychological Model of Civic Identity Formation \/ I. Petrovska \/\/ Journal of Education Culture and Society. \u2013 2021. \u2013 Vol. 12, No. 2. \u2013 P. 167\u2013178.<\/li>\n
  22. Petrovska I. Civic identity development: ontogenetic aspect \/ I. Petrovska \/\/ Social Welfare: Interdisciplinary Approach. \u2013 2019. \u2013 Vol. 9, No. 2. \u2013 P. 29\u201343.<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[65],"tags":[],"_links":{"self":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/12497"}],"collection":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=12497"}],"version-history":[{"count":3,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/12497\/revisions"}],"predecessor-version":[{"id":12580,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/12497\/revisions\/12580"}],"wp:attachment":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=12497"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=12497"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=12497"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}