Methodology for solving problems of classification of appeals/requests of citizens to the “hotline” of the President of the Russian Federation

Бесплатный доступ

The use of neural networks for the classification of text data is an important area of digital transformation of socio-economic systems. The article is devoted to the description of the methodology for classifying citizens' appeals. The proposed technique involves the use of a convolutional neural network. The stages of processing citizens' appeals in the amount of 7000 appeals are described. In order to reduce the dimension of the problem, methods of filtering and removing stop words were applied. The resulting data set allows you to choose the best classifier in terms of accuracy, specificity, sensitivity. Training and test samples were used, as well as cross-validation. The article shows the effectiveness of using this method to distribute requests on 15 topics of citizens' appeals to the “hotline” of the President of the Russian Federation. Automating the classification of received appeals by topic allows them to be processed quickly for further study by the relevant departments. The purpose of the study is automation of the distribution of citizens' appeals to the President's hotline by category based on the use of modern machine learning methods. Materials and methods. The development of software that automates the process of distributing citizens into categories is carried out using a convolutional neural network written in the Python programming language. Results. With the help of the prepared data set, the pre-trained model of NL BERT and sciBERT was trained by the deep learning method. The model shows an accuracy of 86% in the estimates of quality metrics. Conclusion. A pre-trained model was trained using a convolutional neural model using a prepared data set. Even if the forecast does not match the real category, the model gives a minor error, correctly determines the category of the appeal. The results obtained can be recommended for practical application by authors of scientific publications, scientific institutions, editors and reviewers of publishing houses.

Еще

Text processing, machine learning, convolutional neural networks, categorization of text, deep learning, text analysis

Короткий адрес: https://sciup.org/147237451

IDR: 147237451

Список литературы Methodology for solving problems of classification of appeals/requests of citizens to the “hotline” of the President of the Russian Federation

  • Poslaniye Prezidenta Federal'nomu Sobraniyu 15 yanvarya 2020 goda [The President's Message to the Federal Assembly on January 15, 2020]. Available at: http://www.kremlin.ru/events/president/ news/62582 (accessed 20.12.2021). (In Russ.)
  • Poslaniye Prezidenta Federal'nomu Sobraniyu 20 fevralya 2019 goda [The President's Message to the Federal Assembly on February 20, 2019]. Available at: http://www.kremlin.ru/events/president/ news/59863 (accessed 20.12.2021). (In Russ.)
  • Ukaz Prezidenta Rossiyskoy Federatsii ot 07.05.2018 g. N 204 "O natsional'nykh tselyakh i strategicheskikh zadachakh razvitiya Rossiyskoy Federatsii na period do 2024 goda ". Vstupil v silu s 7 maya 2018 goda [Decree of the President of the Russian Federation No. 204 dated 07.05.2018 "On national goals and strategic objectives of the development of the Russian Federation for the period up to 2024". Entered into force on May 7, 2018]. Available at: http://www.kremlin.ru/acts/bank/43027 (accessed 20.12.2021). (In Russ.)
  • Zasedaniye Soveta po strategicheskomu razvitiyu i natsional'nym proyektam 13 iyulya 2020 goda [Meeting of the Council for Strategic Development and National Projects on July 13, 2020]. Available at: http://www.kremlin.ru/events/president/news/63635 (accessed 20.12.2021). (In Russ.)
  • Shagraev A.G. Modifikatsiya, razrabotka i realizatsiya metodov klassifikatsii novostnykh tekstov: avtoref. dis. kand. tekhn. nauk [Modification, development and implementation of methods of classification of news texts. Abstract of Cand. diss.]. Moscow; 2014. 19 p. (In Russ.)
  • Sokolova T.A. An extraction of the elements from bibliography based on automatically generated regular expressions. Information and telecommunication technologies and mathematical modeling of high-tech systems: Materials of the All-Russian conference with international participation. Moscow; 2019. P. 313-316. (In Russ.)
  • Ushakov O.V. [Application of automated information systems with machine learning integration in law enforcement agencies]. Problemy pravovoy i tekhnicheskoy zashchity informatsii. 2018;(6): 142-147. (In Russ.)
  • Donitova V.V., Kireev D.A., Titova E.V., Akimova A.A. Natural language processing models for extraction of stroke risk factors from electronic health records. Trudy Instituta sistemnogo analiza Rossiyskoy akademii nauk = Proceedings of the Institute of system analysis of the Russian academy of sciences. 2021;71(4):93-101. (In Russ.) DOI: 10.14357/20790279210410
  • Kolmogortsev S.V., Sarayev P.V. [Bibliography extraction from texts by regular expressions]. Novyye informatsionnyye tekhnologii v avtomatizirovannykh sistemakh. 2017;(20):82-88. (In Russ.)
  • Gorbachevskaya E.N. Classification of neural networks. Vestnik Volzhskogo universiteta im. V.N. Tatishcheva. 2012;2(19):128-134. (In Russ.)
  • Katenko Yu.V. Application of machine learning methods for text information analysis. Okhrana, bezopasnost', svyaz'. 2019;3(4):90-94. (In Russ.)
  • Voronov V., Martinenko E. Research of parallel structures of neural networks for use in the tasks on the Russian text semantic classification considering limited computing resources (on the example of operational reports used in the RF MIA). Economics and Quality of Communication Systems. 2018;3(9):52-60. (In Russ.)
  • Katenko Yu.V., Petrenko S.A. [The concept of control of the reliability of information in the professional social network using convolutional neural networks]. In: Mezhdunarodnaya konferentsiya po myagkim vychisleniyam i izmereniyam. Vol. 1. St. Petersburg; 2019. P. 140-143. (In Russ.)
  • Muratova U.D. [Studying neural networks for chatbots]. In: Proceedings of the IX Congress of Young Scientists. St. Petersburg; 2021. P. 92-95. (In Russ.)
  • Sukhan' A.A. Applying generative adversarial network to the problem of trend determenition. Moskovskiy ekonomicheskiy zhurnal. 2019;(6):180-191. (In Russ.) DOI: 10.24411/2413-046X-2019-16031
  • Budyl'skiy D.V. [Application of recurrent neural networks in processing natural language texts]. Voprosy nauki. 2015;6:8-12. (In Russ.)
  • Danchenko V.V. Overview of funds development of an information system based on analysis of text perception. Informatika iprikladnaya matematika. 2020;(26):31-34. (In Russ.)
Еще
Статья научная