Network Presentation of Texts and Clustering of Messages

  • Andrey V. OrekhovEmail author
  • Alexander A. Kharlamov
  • Svetlana S. Bodrunova
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11938)


For the purposes of searching for various communities on the Internet, automatic typology of text messages defined via application of methods of cluster analysis may be used. In this paper, we address one of the significant issues in text classification via cluster analysis, namely determination of the number of clusters. For clustering based on semantics, text documents are typically represented in the form of vectors within n-dimensional linear space. What we suggest as a method for determining the number of clusters is the agglomerative clustering of vectors in the linear space. In our work, statistical analysis is combined with neural network algorithms to obtain a more accurate semantic portrait of a text. Then, using the techniques of distributive semantics, mapping of the derived network structures into a vector form is constructed. A statistical criterion for the completion of the clustering process is derived, defined as a Markovian moment. By obtaining automatic partitioning into clusters, one can compare texts that are closest to the centroids with actual content samples or evaluate such texts with the help of experts. If the display of texts in a vector form is adequate, all informational messages from a fixed cluster have the same meaning and the same emotional coloring. In addition, we discuss a possibility to use vector representation of texts for sentiment detection in short texts like search engines input or tweets.


Social network analysis Semantic network Neural network algorithms Distributive semantics Cluster analysis Least squares method Markov moment 



This research in the part of methods evaluation is supported by the Presidential grants of the Russian Federation for young Doctors of Science, grant MD-5962.2018.6.


  1. 1.
    Bodrunova, S.S., Koltsova, O., Koltcov, S., Nikolenko, S.: Who’s Bad? Attitudes toward resettlers from the Post-Soviet South versus other nations in the Russian blogosphere. Int. J. Commun. 11, 3242–3264 (2017)Google Scholar
  2. 2.
    Blekanov, I., Tarasov, N., Maksimov, A.: Topic modeling of conflict ad hoc discussions in social networks. In: Proceedings of the 3rd International Conference on Applications in Information Technology, pp. 122–126. ACM (2018)Google Scholar
  3. 3.
    Chodorow, M.S., Byrd, R.J., Heidorn, G.E.: Extracting semantic hierarchies from a large on-line dictionary. In: Proceedings of the 23rd Annual Meeting on Association for Computational Linguistics (ACL 1985), Stroudsburg, PA, USA, pp. 299–304. Association for Computational Linguistics (1985).
  4. 4.
    Katamba, F.: English Words: Structure, History, Usage, 2nd edn. Routledge, London (2005)Google Scholar
  5. 5.
    Chandler, D.: Semiotics for Beginners: Syntagmatic Analysis. Archived from the original on May 12 (2000)Google Scholar
  6. 6.
    McEnery, T., Wilson, A.: Corpus Linguistics, 2nd edn. Edinburgh University Press, Edinburgh (2001)zbMATHGoogle Scholar
  7. 7.
    Stubbs, M.: Text and Corpus Analysis. Computer Assisted Studies of Language and Culture. Basil Blackwell, Oxford (1996)Google Scholar
  8. 8.
    Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79, 2554–2558 (1982)MathSciNetCrossRefGoogle Scholar
  9. 9.
    McEliece, R.J., Posner, E.C., Rodemic, E.R., Venkatesh, S.S.: The capacity of the Hopfield associative memory. IEEE Trans. Inf. Theory 33(4), 461–482 (1987)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Kharlamov, A.A., Yermolenko, T.V., Zhonin, A.A.: Text understanding as interpretation of predicative structure strings of main text’s sentences as result of pragmatic analysis (combination of linguistic and statistic approaches). In: Železný, M., Habernal, I., Ronzhin, A. (eds.) SPECOM 2013. LNCS (LNAI), vol. 8113, pp. 333–339. Springer, Cham (2013). Scholar
  11. 11.
    Kharlamov, A.A., Yermolenko, T.V., Zhonin, A.A.: Modeling of process dynamics by sequence of homogenous semantic networks on the base of text corpus sequence analysis. In: Ronzhin, A., Potapova, R., Delic, V. (eds.) SPECOM 2014. LNCS (LNAI), vol. 8773, pp. 300–307. Springer, Cham (2014). Scholar
  12. 12.
    Kharlamov, A.A., Ermakov, A.E., Kuznetsov, D.M.: TextAnalyst komplexniy neurosetevoy analyzator textovoy informacii [Complex Neuronetwork Analyzer of Text Information TextAnalyst]. Vestnik moskovskogo gosudarstvennogo tekhnicheskogo universyteta im. N.E. Baumana. Seriya: Mashinostroenie [Bulletin of Moscow State Tekhnikal University by N.E. Bauman. Series: Mechanik Engeneering], no. 1, 121–126 (1998). (in Russian)Google Scholar
  13. 13.
    Kharlamov, A.A., Ermakov, A.E., Kuznetsov, D.M.: Systema dlya avtomaticheskoy smyslovoy obrabotky textov na osnove neyrostevoy nekhnologii TextAnalyst [System of Automatical Semantic Text Processing Based on Neuronetwork TextAnalyst Technology]. Informatsionniye Tekhnologii [Informational Technology], no. 10, 27–32 (1999). (in Russian)Google Scholar
  14. 14.
    Kharlamov, A.A., Yermolenko, T.V.: Neiyrosetevaya sreda (neuromophnaya associativnaya pamyat) dlya preodoleniya informatsionnoy sloshnosty. Poisk smysla dlya slabostrukturirovannykh massivakh informatsii. Chyast I. Strukturnaya obrabotka informatsii v kore [Neuronetwork Environment (Neuromorphic Associative Memory) for Information Complexity Overcoming. Searching of Sense in Weak Structured Information Arrays. Part I. Structural Information Processing in Cortex]. Informatsionniye tekhnologii [Informational Technology] 21(11), 814–820 (2015). (in Russian)Google Scholar
  15. 15.
    Kharlamov, A.A., Yermolenko, T.V.: Neiyrosetevaya sreda (neuromophnaya associativnaya pamyat) dlya preodoleniya informatsionnoy sloshnosty. Poisk smysla d slabostrukturirovannykh massivakh informatsii. Chyast I. Obrabotka informatsii v gippokampe [Neuronetwork Environment (Neuromorphic Associative Memory) for Information Complexity Overcoming. Searching of Sense in Weak Structured Information Arrays. Part II. Information Processing in Hyppocampus]. Informatsionniye tekhnologii. [Informational Technology] 21(11), 883–889 (2015). (in Russian)Google Scholar
  16. 16.
    Kharlamov, A.A.: Tekhnologiya avtomaticheskogo smyslovogo analiza textov TextAnalyst [Automatical Semantic Text Analysis TextAnalyst]. Vestnik moskovskogo gosudarstvennogo universiteta. Gumanitarnye nauki [Bulletin of Moscow State Linguistic University Human Scienses], no. 699, 234–244 (2014). (in Russian)Google Scholar
  17. 17.
    Geger, A.E., Geger, S.A.: Otechestvennye komputernye progremmy dlya analysa kachestvennykh dannykh: Vega I TextAnalyst [Native Computer Program for Quality Data Analysis: Vega and TextAnalyst]. Aktual nye voprosy obchestvennykh nauk: sotsyologiya, politologiya, philosophiya, istoriya [Up-to-the-minute Questions of Social Scienses: Sociology, Politology, Philosophy, History], no. 46, 34–40 (2015). (in Russian)Google Scholar
  18. 18.
    Ore, O.: Theory of Graphs. American Mathematical Society, Providence (1983)zbMATHGoogle Scholar
  19. 19.
    Schutze, H.: Dimensions of meaning. In: Proceedings of Supercomputing 1992, pp. 787–796 (1992)Google Scholar
  20. 20.
    Clark, S.: Vector space models of lexical meaning. In: Handbook of Contemporary Semantics, 2nd edn. Blackwell, Oxford (2014)Google Scholar
  21. 21.
    Kiela, D., Clark, S.: A systematic study of semantic vector space model parameters. In: Conference: Proceedings of the 2nd Workshop on Continuous Vector Space Models and Their Compositionality (CVSC) (2014).
  22. 22.
    Orekhov, A.V.: Markov moment for the agglomerative method of clustering in Euclidean space. Vestn. St. Petersburg Univ. Appl. Math. Comput. Sci. Control Process. 15(1), 76–92 (2019). Scholar
  23. 23.
    Everitt, B.S.: Cluster Analysis, 5th edn. Wiley, Chichester (2011)CrossRefGoogle Scholar
  24. 24.
    Aldenderfer, M.S., Blashfield, R.K.: Cluster Analysis. Sage Publications, Inc., Beverly Hills (1984)CrossRefGoogle Scholar
  25. 25.
    Orekhov, A.V.: Agglomerative method for texts clustering. In: Bodrunova, S.S., et al. (eds.) INSCI 2018. LNCS, vol. 11551, pp. 19–32. Springer, Cham (2019). Scholar
  26. 26.
    Wald, A.: Sequential Analysis. Wiley, New York (1947)zbMATHGoogle Scholar
  27. 27.
    Sirjaev, A.N.: Statistical Sequential Analysis: Optimal Stopping Rules. American Mathematical Society, Providence (1973)Google Scholar
  28. 28.
    Chow, Y.S., Robbins, H.E., Siegmund, D.: Great Expectations: The Theory of Optimal Stopping. Houghton Mifflin, Boston (1971)zbMATHGoogle Scholar
  29. 29.
    Shiryaev, A.N.: Optimal Stopping Rules. Springer, Heidelberg (2009). Scholar
  30. 30.
    Orekhov, A.V.: Criterion for estimation of stress-deformed state of SD-materials. In: AIP Conference Proceedings, vol. 1959, p. 070028 (2018).
  31. 31.
    Orekhov, A.V.: Approximation-evaluation tests for a stress-strain state of deformable solids. Vestn. St. Petersburg Univ. Appl. Math. Comput. Sci. Control Process. 14(3), 230–242 (2018). Scholar
  32. 32.
    Bodrunova, S.S., Blekanov, I., Maksimov, A.: Topics in the Russian Twitter and relations between their interpretability and sentiment. Submitted to the SAMSN International Workshop, Barcelona, Spain, pp. 1–6 (2019, unpublished)Google Scholar
  33. 33.
    Radev, D.R., Blair-Goldensohn, S., Zhang, Z.: Experiments in single and multidocument summarization using MEAD. In: Proceedings of the First Document Understanding Conference, pp. 1–8 (2001)Google Scholar
  34. 34.
    Nur’Aini, K., Najahaty, I., Hidayati, L., Murfi, H., Nurrohmah, S.: Combination of singular value decomposition and K-means clustering methods for topic detection on Twitter. In: Proceedings of the 2015 International Conference on Advanced Computer Science and Information Systems (ICACSIS), pp. 123–128. IEEE (2015)Google Scholar
  35. 35.
    Aggarwal, C.C., Zhai, C.: Mining Text Data. Springer, Boston (2012). Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.St. Petersburg State UniversitySt. PetersburgRussian Federation
  2. 2.Institute of Higher Nervous Activity and Neurophysiology of Russian Academy of SciencesMoscowRussian Federation
  3. 3.Moscow State Linguistic UniversityMoscowRussian Federation
  4. 4.Higher School of EconomicsMoscowRussian Federation

Personalised recommendations