Neural network technologies for analysis of opinion tonality for realization of human-oriented concept of urban environment transformation

Dmitrii Yu. Voronin, Pavel N. Kuznetsov, Vladislav P. Evstigneev, Rajisa N. Litvinova, Sergei A. Mityagin


The basis of the smart sustainable city’s concept lies in application of the end-to-end digital technologies to improve organization of urban processes and innovative services. However, nowadays, there is an acute need in transition from a technology-oriented to a human-oriented paradigm of “sustainable smart cities” taking into account personal demands of citizens and various social groups rather than just implementing modern technical innovations. The present study deals with application of artificial neural network to informational support of effective decisions within implementation of the human-oriented concept of transformation of the urban environment. An example of such an informational support for the concept to be realized using a recursive neural network with long short-term memory is provided. Highly accurate (over 95%) automated analysis of tonality of citizens’ opinions on implementation of innovations into the urban environment has been performed using social media data.

Full Text:

PDF (Russian)


Gubanov D.A., Novikov D.A., Chkhartishvili A.G. Social networks: models of informational influence, management and confrontation. –3rd ed.– M.: MCME, 2018. – 224 p. (in Russian)

Gubanov D.A., Novikov D.A., Chkhartishvili A.G. Models of reputation and information management in social networks // Mathematical theory of games and its applications. – 2009. – №2. – P. 14 – 37. (in Russian)

Mityagin S.A., Voronin D.Yu., Sobolevsky S.L., Drozhzhin A.I., Evstigneev V.P., Sadovnikova N.P., Parygin D.S., Chugunov A.V. Digital model of the city: principles and approaches to implementation // International journal of open information technologies. – 2019. – №7 (12). – P. 94 – 103. (in Russian)

Tarasov D.S. Deep Recurrent Neural Networks for Multiple Language Aspect-Based Sentiment Analysis // Proceedings of the International Conference “Dialogue-2015” (Moscow, Russia, May 27–30, 2015), Computational Linguistics and Intellectual Technologies, 2015. P. 65 –74.

Prabowo R., Thelwall M. Sentiment analysis: A combined approach // Journal of Informetrics. – 2009. – №2. – P. 143 – 157.

Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. Bert. Pre-training of deep bidi-rectional transformers for language understanding // ArXiv. Preprint arXiv:1810.04805 – 2018.

Tandel S. S., Jamadar A., Dudugu S. A. Survey on Text Mining Techniques // 5th International Conference on Advanced Computing & Communication Systems (ICACCS). – IEEE, 2019. – P. 1022 –1026.

Kuckartz U. Qualitative text analysis: A systematic approach // Compendium for early career researchers in mathematics education. – Springer, Cham, 2019. – P. 181 – 197.

Belyakov M.V. Analysis of news messages on the website of the Ministry of Foreign Affairs of the Russian Federation by the method of content analysis // Bulletin of the Peoples' Friendship University of Russia. Series: theory of language, semiotics, semantics. – 2016. – №4. – P. 115 – 124.

Dudina V.I., Yudina D.I. Extracting opinions from the Internet: can text analysis methods replace polls? // Monitoring public opinion: Economic and social changes. – 2017. – № 5. – P. 63 –78. (in Russian)

Youngchul C., Junghoo C. Social-network analysis using topic models // Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval (SIGIR '12). – ACM, NY. – 2012. P. 565 – 574.

Huang X. et al. Learning from networks: Algorithms, theory, and applications // Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. – 2019. – P. 3221 – 3222.

Yousefi Nooraie R. et al. Social network analysis: An example of fusion between quantitative and qualitative methods // Journal of Mixed Methods Research. – 2020. – Vol. 14. – № 1. – P. 110 – 124.

Y. Chen, J. Hu, H. Zhao, Y. Xiao, P. Hui. Measurement and Analysis of the Swarm Social Network with Tens of Millions of Nodes // IEEE Access. – 2018. – P. 4547 – 4559.

Truong Q. D., Truong Q. B., Dkaki T. Graph Methods for Social Network Analysis // International Conference on Nature of Computation and Communication. – Springer, Cham, 2016. – P. 276 – 286.

Taniarza N., Maharani W. Social network analysis using k-Path centrality method // Journal of Physics: Conference Series. 2018. Vol. 971.

Yang J., McAuley J., Leskovec J. Community Detection in Networks with Node Attributes // 13th International Conference on Data Mining, Dallas, TX, 2013. – P. 1151 – 1156.

Lee C., Wilkinson D. J. A Social Network Analysis of Articles on Social Network Analysis // ArXiv. – 2018. – abs/1810.09781.

Sun L. et al. An optimized clustering method with improved cluster center for social network based on gravitational search algorithm // International Conference on Industrial IoT Technologies and Applications. – Springer, Cham, 2017. – P. 61 – 71.

Sun Y., Yin S., Li H., Teng L., Karim S. GPOGC: Gaussian Pigeon-Oriented Graph Clustering Algorithm for Social Networks Cluster // IEEE Access.– 2019. Vol. 7 –– P. 99254 – 99262

Fortunato S. Community detection in graphs. Physics Reports // ArXiv.– 2010. – №486. – P. 75 – 174.

Smelser N. J. Theory of Collective Behavior. – London: Routledge, 2013. – 484 p.

Garr, T.R. Why do people rebel [Text] / T. R. Garr. - St. Petersburg: Peter, 2005. – 461 p. (in Russian)

McAdam D., S. Tarrow, C. Tilly. Dynamics of Contention. – Cambridge: Cambridge University Press, 2001. – 412 p.

Opp K. D. Theories of Political Protest and Social Movements. – New York: Routledge, 2009. – 424 p.

Kendall D. Sociology in Our Times. – Boston: Massachusetts: Cengage Learning, 2012. – 704 p.

Sak H., Senior A., Beaufays F. Long short-term memory recurrent neural network architectures for large-scale acoustic modeling // Proceedings of the Annual Conference of the International Speech Communication Association. 2014. – P. 338-342.

Xiangang L., Xihong W. Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition // IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2015. – P. 4520 – 4524. DOI: 10.1109/ICASSP.2015.7178826.


  • There are currently no refbacks.

Abava  Absolutech Convergent 2020

ISSN: 2307-8162