Abstract
The paper deals with the urgent issue of improving the professional software for text statistical analysis in accordance with the needs of specialists. Peculiarities and prospects of statistical research in linguistics are analyzed and information technology (IT) for determining the statistical profile of Ukrainian-language texts is developed. Complex work on modelling the software system was carried out, it was presented in the corresponding schemes and diagrams, which integrally reflect the functioning and purpose of the developed product. Mathematical and system bases of statistical analysis aimed at automation of professional processing of Ukrainian-language texts, in the context of introducing the offered information technology are considered. The structural scheme of the project decision is constructed and the main requirements for hardware are defined. The components of information technology are developed, and the software system structure is proposed, which is based on the modular principle. Mathematical support for IT has been developed, it is based on the methods of applied statistics and allows determining the main characteristics (statistical profile) of the studied Ukrainian-language texts. In addition, the algorithms and software for IT have been developed using Python. The results of research on Ukrainian-language texts and their statistical profiles are given, it is shown that the developed information technology provides processing of Ukrainian-language texts with a high level of automation. The obtained results can be considered as a contribution to the development of scientific research in linguistics, which creates conditions for the study of authors texts of different styles and the effective use of professional skills and knowledge by a wide range of users. The scientific novelty of the work is that a model of automated determination of the statistical profile of Ukrainian language texts has been developed, which provides an opportunity for a comprehensive study of the corpus of Ukrainian-language texts. The obtained results are also of practical significance, as the structural scheme of IT has been developed, software tools of information technology for automation of the determining the statistical profile of Ukrainian-language texts have been implemented, and the results of text investigation have been analyzed.
Publisher
Lviv Polytechnic National University
Reference23 articles.
1. [1] Bisikalo, O. V., & Kravchuk, I. A. (2010, November). Analysis of the morphological structure of the word based on the associative-statistical approach. Journal of Vinnytsia Polytechnic Institute, 4, 134-136. Retrieved from: www.visnyk.vntu.edu.ua/index.php/visnyk/article/view/1495
2. [2] Buk, S. N., & Rovenchak, A. A. (2004). Rank-Frequency Analysis for Functional Style Corpora of Ukrainian. Journal of Quantitative Linguistics, 11(3), 161-71. https://doi.org/10.1080/0929617042000314912
3. [3] Grabar, N., & Thierry, H. (2017, April). Creation of a multilingual aligned corpus with Ukrainian as the target language and its exploitation. Computational linguistics and intelligent systems (COLINS 2017): proceedings of the 1st International conference, National Technical University "KhPI", 10-19. Retrieved from: http://ena.lp.edu.ua:8080/handle/ntb/39454
4. [4] Grodniewicz, J. P. (2021). The process of linguistic understanding. Synthese, 198, 11463-11481. https://doi.org/10.1007/s11229-020-02807-9
5. [5] Hlushchenko, V. A. (2010). Linguistic method and its structure. Linguistics, 6, 32-44. Retrieved from: http://nbuv.gov.ua/UJRN/MoZn_2010_6_5