A.S. Volkov1, M.V. Chernenky2, E. Yu. Silantieva3

1,2 Bauman Moscow State Technical University (Moscow, Russia)

The task of sentiment analysis is to identify the emotional attitude of the author of the text to the subject or topic under discussion.

The relevance of the task is largely related to the development of social networks, online recommendation systems and other services containing a large number of people's opinions on various topics, in particular, about goods, services, offers, events, etc. It is important for marketers, sociologists, administrators, politicians, managers to know people's opinions. The article proposes a solution to the problem of sentiment analysis by decomposing the recognition procedure into two stages using several neural networks and dividing the analyzed texts into homogeneous subsets.

The aim of the work is to create a more reliable procedure for determining people's opinions based on their reaction to various messages from the Internet.

A decomposition technique for organizing a two-stage process of analyzing the sentiment of texts in Russian by training separate neural networks for each subset of data has been developed and practically implemented. This technique combines two levels of information processing: the first level of a neural network classifier and the second level, which includes several neural network analyzers.

The proposed two-stage procedure for analyzing the sentiment of the text makes it possible to ensure the scalability of applications, the independence of neural network settings management and to increase the reliability of estimates.

Volkov A.S., Chernenky M.V., Silantieva E.Yu. Two-stage procedure of neural network sentiment analysis for texts in russian. Dynamics of complex systems. 2021. T. 15. № 4. Р. 5−13. DOI: 10.18127/j19997493-202104-01 (In Russian)

1. Noskov D.V. Klassifikaciya tekstov pri pomoshchi algoritmov mashinnogo obucheniya. Vestnik nauki i obrazovaniya. 2018. №4 (40) (In Russian).
2. Parhomenko P.A., Grigor'ev A.A., Astrahancev N.A. Obzor i eksperimental'noe sravnenie metodov klasterizacii tekstov. Trudy ISP RAN. 2017. № 2 (In Russian). 
3. Kozlov P.Yu. Sposoby predstavleniya tekstovoj informacii pri avtomatizirovannom rubricirovanii korotkih tekstovyh dokumentov. Programmnye produkty i sistemy. 2017. № 4 (In Russian).
4. Abramov P.S. Izvlechenie klyuchevoj informacii iz teksta. Novye informacionnye tekhnologii v avtomatizirovannyh sistemah. 2018.  № 21 (In Russian).
5. Kulikova N.R. Avtomaticheskaya generaciya teksta (na primere novosti figurnogo kataniya). Cifrovaya nauka. 2020. № 6 (In Russian).
6. Semina T.A. Analiz tonal'nosti teksta: sovremennye podhody i sushchestvuyushchie problemy. Social'nye i gumanitarnye nauki. Otechestvennaya i zarubezhnaya literatura. Ser. 6, Yazykoznanie: Referativnyj zhurnal. 2020. № 4 (In Russian).
7. Bol'shakova E.I., Voroncov K.V., Efremova N.E., Klyshinskij E.S., Lukashevich N.V., Sapin A.S. Avtomaticheskaya obrabotka tekstov na estestvennom yazyke i analiz dannyh: ucheb. posobie. M.: Izd-vo NIU VSHE. 2017. 269 s. (In Russian).Roh Y., Heo G., Whang S.E. A Survey on Data Collection for Machine Learning: A Big Data – AI Integration Perspective. IEEE Transactions on Knowledge and Data Engineering. 2021. V. 33. № 4. P. 1328–1347. 
8. Di Nunzio G. M., Vezzani F. A Linguistic Failure Analysis of Classification of Medical Publications: A Study on Stemming vs Lemmatization. In Cabrio E., Mazzei A., Tamburini F. (Eds.), Proceedings of the Fifth Italian Conference on Computational Linguistics CLiC-it 2018: 10–12 December 2018, Torino. Torino: Academia University Press. 2018. 
9. Amjad M., Gelbukh A. Voronkov I. Saenko A. Comparison of Text Classification Methods using Deep Learning Neural Networks. Proceedings of the 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing). 2019.
10. Dang N.C., Moreno-García M.N., De la Prieta F. Sentiment Analysis Based on Deep Learning: A Comparative Study. Electronics. 2020. V. 9(3). P. 483.
11. Gonzalez-Garcia A., Modolo D., Ferrari V. Do Semantic Parts Emerge in Convolutional Neural Networks? International Journal of Computer Vision. 2018. V. 126. 
12. Alzubaidi L., Zhang J., Humaidi A.J. et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data Proceedings 8, 53 (2021).
13. Rogers A., Romanov A., Rumshisky A., Volkova S., Gronas M., Gribov A. RuSentiment: An Enriched Sentiment Analysis Dataset for Social Media in Russian. In Proceedings of the 27th International Conference on Computational Linguistics (P. 755–763). Association for Computational Linguistics. 2018.