Publishing house Radiotekhnika

"Publishing house Radiotekhnika":
scientific and technical literature.
Books and journals of publishing houses: IPRZHR, RS-PRESS, SCIENCE-PRESS

Тел.: +7 (495) 625-9241


Research of social media users’ messages based on relational concept analysis


E.V. Kotelnikov – Ph.D. (Eng.), Associate Professor, Head of Department of fundamental informatics, Vyatka State University
V.R. Milov – Dr.Sc. (Eng.), Professor, Head of Department “Electronics and Computers Networks”, Nizhny Novgorod State Technical University n.a. R.E. Alekseev

Currently, various types of social media, such as blogs and microblogs, social networks and forums, are of considerable research interest: big data sets containing opinions of users on different objects (public persons, organizations, goods) are available in electronic form and can be analyzed using automatic methods.
The article proposes an approach for extracting the opinions of social media users on the basis of the Relational Concept Analysis (RCA) method, which is an extension of the Formal Concept Analysis (FCA) method by taking into account the relationships between objects, which allows to identify more complex structures and dependencies. When analyzing relational concepts, the family of lattices is formed using the Multi-FCA iterative algorithm.
An example of the analysis of the social media users’ opinions is given on the basis of the study of text messages from various Internet sources about Kirov region’s monotowns. The input data in this case are user messages in which the sentiment of the opinion (positive, negative, neutral or contradictory) and aspects of life in a monotown (authorities, education, road conditions, cultural events) are marked out. Social-demographic characteristics of users (for example, gender) and connections (authorship) between users and messages are also given. The result of the RCA method is a concept lattice, the analysis of which allows to reveal the hidden dependencies associated with the opinions of socio-demographic groups in relation to various aspects of life in monotowns.
In the future a perspective research direction is the ways to evaluate the finding concepts, for example, by the degree of significance and explanatory ability, which would allow in the automated mode to put forward and rank the corresponding hypotheses regarding the initial data, including the opinions of users of social media.

  1. Murphy J., Hill C.A., Dean E. Social Media, Sociality and Survey Research / C.A. Hill, E. Dean, J. Murphy (Eds.) Social Media, Sociality and Survey Research. Wiley. 2013.
  2. Murphy J., Link M., Childs J., Tesfaye C., Dean E., Stern M. Social Media in Public Opinion Research // Report of the AAPOR Task Force on Emerging Technologies in Public Opinion Research. Deerfield, IL: American Association for Public Opinion Research. 2014.
  3. Liu B. Sentiment Analysis and Opinion Mining // Synthesis Lectures on Human Language Technologies. 2012. V. 5(1).
  4. Witten I.H., Frank E., Hall M.A. Data Mining. Practical Machine Learning Tools and Techniques. 3rd ed. Elsevier. 2011.
  5. Zafarani R., Abbasi M.A., Liu H. Social Media Mining: an Introduction. Cambridge University Press. 2014.
  6. Filimonov A.V., Osipov A.V., Klimov A.B. Primenenie nejronny'x setej dlya vy'yavleniya trollej v soczial'ny'x setyax // Nejrokomp'yutery': razrabotka, primenenie. 2015. № 8. S. 87–92.
  7. Rouane-Hacene M., Huchard M., Napoli A., Valtchev P. A proposal for combining formal concept analysis and description logics for mining relational data // Proceedings of the 5th Intl. Conf. on Formal Concept Analysis (ICFCA’07). LNCS. V. 4390. Springer. 2007. P. 51–65.
  8. Rouane-Hacene M., Huchard M., Napoli A., Valtchev P. Relational concept analysis: mining concept lattices from multi-relational data // Ann. Math. Artif. Intell. 2013. V. 67. P. 81–108.
  9. Ganter B., Wille R. Formal Concept Analysis: Mathematical Foundations. Springer. 1999.
  10. Snasel V., Horak Z., Abraham A. Understanding social networks using Formal Concept Analysis // Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology. 2008. V. 3. P. 390–393.
  11. Cuvelier E., Aufaure M.-A. A buzz and e-reputation monitoring tool for Twitter based on Galois Lattices // Proceedings of ICCS'2011: Conceptual Structures for Discovering Knowledge. 2011. Derby. UK. P. 91–103.
  12. Krajci S. Social Network and Formal Concept Analysis // Social Networks: A Framework of Computational Intelligence / Pedrycz W., Chen S.-M. (Eds.). Springer. 2014.
  13. Guesmi S., Trabelsi C., Latiri C. Community Detection in Multi-relational Bibliographic Networks // Hartmann S., Ma H. (Eds.). Database and Expert Systems Applications. DEXA 2016. Lecture Notes in Computer Science, V. 9828. Springer, Cham. P. 11–18.
  14. Krajca P., Outrata J., Vychodil V. Advances in algorithms based on CbO // Proceedings of the 8th International Conference on Concept Lattices and Their Applications (CLA). 2010. V. 672. P. 325–337.
  15. Andrews S. A ‘Best-of-Breed’ approach for designing a fast algorithm for computing fixpoints of Galois Connections // Information Sciences, 2015. V. 295(20). P. 633–649.
  16. Kuznetsov S., Obiedkov S. Comparing performance of algorithms for generating concept lattices // J. Exp. Theor. Artif. Intell. 2002. V. 14. P. 189–216.
  17. Rasporyazhenie Pravitel'stva RF № 1398-r ot 29 iyulya 2014 g. «Ob utverzhdenii perechnya monogorodov».
  18. Kotel'nikov E.V. Abduktivny'j logicheskij vy'vod dlya analiza tonal'nosti tekstov na osnove DSM-metoda // Fundamental'ny'e issledovaniya. 2015. № 2(13). S. 2801–2805.
May 29, 2020

© Издательство «РАДИОТЕХНИКА», 2004-2017            Тел.: (495) 625-9241                   Designed by [SWAP]Studio