An opinion mining monitoring model for social networks introduced. The model includes text mining processing over social network data and uses sentiment analysis approach in particular. Practical usage results of software implementation and its requirements described as well as further research directions.
social network, monitoring, sentiment analysis, neural networks, deep learning.
1. Averchenkov, V. I. Representation and processing of indistinct information in multi-criteria models of decision-making for management tasks of social and economic systems / V.I. Averchenkov, A.V. Lagerev, A.G. Podvesovsky // Bulletin of Bryansk State Technical University. – 2012. – No. 2 (34). – pp. 97-104.
2. Bazenkov, N. I. Review of information systems for social networks analysis / N.I. Bazenkov, D.A. Gubanov // Management of large systems: Proceedings – M.: ICS RAS, 2013. – No. 41. – pp. 357-394.
3. Vasilyev, V.G. Sentiment classification by fragment rules / V.G. Vasilyev, M.V. Khudyakova, S.A. Davydov // Computational linguistics and intellectual technologies: Proceedings of the Annual International Conference "Dialogue": Proceedings. – M.: Publishing House of RSUTE, 2011. – Vol. 2. – pp. 66-76.
4. Gubanov, D.A. Conceptual approach to online social networks analysis / D.A. Gubanov, A.G. Chkhartishvili // Management of large systems: Proceedings. – M.: ICS RAS, 2013. – No. 45. – pp. 226-236.
5. Gubanov, D.A. Model of informational influence and information control in social networks / D.A. Gubanov, D A. Novikov, A G. Chkhartishvili // Problems of management. – M.: SenSiDat-Kontrol, 2009. – No. 5. – pp. 28-35.
6. Gubanov, D.A. Social networks: models of information influence, control and confrontation / D.A. Gubanov, D.A. Novikov, A.G. Chkhartishvili. – M.: Publishing House of Phys.-Math. lit., 2010. – 228 p.
7. For what do people use Internet? – URL: http://fom.ru/SMI-i-internet/11088.
8. Internet in Russia: dynamics of penetration. Summer of 2014. – URL: http://fom.ru/SMI-i-internet/11740.
9. Menshikov, I.L. Sentiment analysis in Russian by means of graph models / I.L. Menshikov // Proceedings of the All-Russian Scientific Conference AIST´2013: Proceedings. – Yekaterinburg, 2013. – pp. 151-155.
10. Pak, A. Teaching feelings to computer (sentiment analysis in Russian). – URL: http://habrahabr.ru/post/149605.
11. Paklin, N.B. Business analytics: from data to knowledge: Manual / N.B. Paklin, V.I. Oreshkov. – 2d Edition. – SPb.: St. Petersburg, 2013. – 704 p.
12. Panicheva, P.V. ATEX: a rule-based sentiment analysis system processing texts in various topics / P.V. Panicheva // Computational linguistics and intellectual technologies: Computational linguistics and intellectual technologies: Proceedings of the Annual International Conference "Dialogue": Proceedings. – M.: Publishing House of RSUTE, 2013. – Vol. 2. – pp. 101-112.
13. Podvesovsky, A.G. Features of social networks monitoring and sentiment analysis software implementation / A.G. Podvesovsky, D.V. Budylsky // Questions of information technologies: International Proceedings. – Lipetsk: Gravis, 2014. – Issue I. – pp. 23-33.
14. Brand Analytics – monitoring system and the analysis of social media. – URL: http://br-analytics.ru.
15. BrandSpotter – monitoring system of social media. – URL: http://brandspotter.ru.
16. Deng, L. Deep Learning: Methods and Applications/L. Deng, Y. Dong. – Now Publishers, 2014. – 134 p.
17. IQBuzz – professional monitoring service for marketing specialists, PR and SMM. – URL: http://iqbuzz.ru.
18. Socher, R. Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank/R. Socher [et al.]//EMNLP. – 2013. – P. 1-12.
19. YouScan.ru – monitoring system of social media and social networks. – URL: http://youscan.ru