Social Network Sentiment Analysis and Message Clustering

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


Till today, classification of documents into negative, neutral, or positive remains a key task within the analysis of text tonality/sentiment. There are several methods for the automatic analysis of text sentiment. The method based on network models, the most linguistically sound, to our viewpoint, allows us take into account the syntagmatic connections of words. Also, it utilizes the assumption that not all words in a text are equivalent; some words have more weight and cast higher impact upon the tonality of the text than others. We see it natural to represent a text as a network for sentiment studies, especially in the case of short texts where grammar structures play a higher role in formation of the text pragmatics and the text cannot be seen as just “a bag of words”. We propose a method of text analysis that combines using a lexical mask and an efficient clustering mechanism. In this case, cluster analysis is one of the main methods of typology which demands obtaining formal rules for calculating the number of clusters. The choice of a set of clusters and the moment of completion of the clustering algorithm depend on each other. We show that cluster analysis of data from an n-dimensional vector space using the “single linkage” method can be considered a discrete random process. Sequences of “minimum distances” define the trajectories of this process. “Approximation-estimating test” allows establishing the Markov moment of the completion of the agglomerative clustering process.


Message clustering Sentiment analysis Markov moment Tonality Lexical mask Approximation-estimation test Short texts Twitter 



This research in the part of data interpretation and literature review has been supported by the Russian Science Foundation grant 16-18-10125-P (2016–2018, prolongued for 2019–2020).


  1. 1.
    Pang, B., Lee, L.: Opinion mining and sentiment analysis. Found. Trends Inf. Retrieval 2, 1–135 (2008)CrossRefGoogle Scholar
  2. 2.
    Liu, B.: Sentiment analysis and subjectivity. In: Indurkhyaé, N., Damerau, F.J. (eds.) Handbook of Natural Language Processing, vol. 2, pp. 627–666 (2010)Google Scholar
  3. 3.
    Turney, P.: Thumbs up or thumbs down? semantic orientation applied to unsupervised classification of reviews. In: Proceedings Association for Computational Linguistics, pp. 417–424 (2002). arXiv:cs.LG/0212032
  4. 4.
    Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? sentiment classification using machine learning techniques. Proc. EMNLP 10, 79–86 (2002)CrossRefGoogle Scholar
  5. 5.
    Bodrunova, S.S., Blekanov, I.S., Smoliarova, A., Litvinenko, A.: Beyond left and right: real-world political polarization in Twitter discussions on inter-ethnic conflicts. Media Commun. 7(3), 119–132 (2019)CrossRefGoogle Scholar
  6. 6.
    Bollen, J., Mao, H., Zeng, X.-J.: Twitter mood predicts the stock market. J. Comput. Sci. 2(1), 1–8 (2011)CrossRefGoogle Scholar
  7. 7.
    Pang, B., Lee, L.: Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales. In: Proceedings 43rd Annual Meeting Association for Computational Linguistics, University of Michigan, USA, June 25-30, 115–124 (2005)Google Scholar
  8. 8.
    Snyder, B., Barzilay, R.: Multiple aspect ranking using the good grief algorithm. In: Proceedings Joint Human Language Technology/North American Chapter of the ACL Conference (HLT-NAACL), pp. 300-307 (2007)Google Scholar
  9. 9.
    Thelwall, M., Buckley, K., Paltoglou, G., Cai, D., Kappas, A.: Sentiment strength detection in short informal text. J. Am. Soc. Inf. Sci. Technol. 61(12), 2544–2558 (2010)CrossRefGoogle Scholar
  10. 10.
    Su, F., Markert, K.: From words to senses: a case study in subjectivity recognition. In: Proceedings 22nd International Conference on Computational Linguistics, vol. 1, pp. 825–832, ACL (2008)Google Scholar
  11. 11.
    Pang, B., Lee, L.: A sentimental education: sentiment analysis using subjectivity. In: Proceedings 42nd Annual Meeting, Association for Computational Linguistics, pp. 271–278 (2004)Google Scholar
  12. 12.
    Washington, E.: Human Sentiment Analysis. Last accessed 14 Nov 2013Google Scholar
  13. 13.
    Pandey, A.C., Rajpoot, D.S., Saraswat, M.: Twitter sentiment analysis using hybrid cuckoo search method. Inf. Process. Manag. 53(4), 764–779 (2017)CrossRefGoogle Scholar
  14. 14.
    Pazelskaya, A., Soloviev, A.: Method of determining emotions in texts in Russian. In: The International Conference on Computational Linguistics and Intellectual Technologies “Dialogue-2011”, Moscow, 510–522 (2011) [in Russian]Google Scholar
  15. 15.
    Chetviorkin, I., Loukachevitch, N.: Extraction of russian sentiment lexicon for product meta-domain. Proc. COLING 2012, 593–610 (2012)Google Scholar
  16. 16.
    Klekovkina, M.V., Kotelnikov, E.V.: The method of automatic classification of texts by tonality, based on the dictionary of emotional vocabulary. Trudy 14–i Vserossiyskoi nauchnoi konferentsii “Elektronnye biblioteki: Perspektivnye metody i tekhnologii, elektronnye kollektsii”, pp. 81–86 (2012) [in Russian]Google Scholar
  17. 17.
    Ustalov, D.A.: Extraction of terms from the Russian texts using the graph models. In: Proceedings Conference Graphs Theory and Applications, pp. 62–69 (2012). [in Russian]Google Scholar
  18. 18.
    Kobayashi, N., Iida, R., Inui, K., Matsumoto, Y.: Opinion mining on the web by extracting subject-aspect-evaluation relations. In: AAAI Spring Symposium: Computational Approaches to Analyzing Weblogs, pp. 86–91 (2006)Google Scholar
  19. 19.
    Ogneva, M.: How Companies Can Use Sentiment Analysis to Improve Their Business. Last accessed 13 Dec 2012Google Scholar
  20. 20.
    Rentoumi, V., Giannakopoulos, G., Karkaletsis, V., Vouros, G.A.: Sentiment analysis of figurative language using a word sense disambiguation approach. In: Proceedings International Conference RANLP-2009, pp. 370–375 (2009)Google Scholar
  21. 21.
    von Stieglitz, S., Dang-Xuan, L., Bruns, A., Neuberger, C.: Social media analytics-an interdisciplinary approach and its implications for information systems. Bus. Inf. Syst. Eng. 6(2), 89–96 (2014)CrossRefGoogle Scholar
  22. 22.
    Girvan, M., Newman, M.E.: Community structure in social and biological networks. Proc. Nat. Acad. Sci. 99(12), 7821–7826 (2002)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Deitrick, W., Hu, W.: Mutually enhancing community detection and sentiment analysis on twitter networks. J. Data Anal. Inf. Process. 1(03), 19–29 (2013)Google Scholar
  24. 24.
    Xia, R., Zong, C., Li, S.: Ensemble of feature sets and classification algorithms for sentiment classification. Inf. Sci. 181(6), 1138–1152 (2011)CrossRefGoogle Scholar
  25. 25.
    Li, N., Wu, D.D.: Using text mining and sentiment analysis for online forums hotspot detection and forecast. Dec. Support Syst. 48(2), 354–368 (2010)CrossRefGoogle Scholar
  26. 26.
    Scheible, C.: Sentiment translation through lexicon induction. In: Proceedings ACL 2010 Student Research Workshop, pp. 25–30 (2010)Google Scholar
  27. 27.
    Burscher, B., Vliegenthart, R., Vreese, C.H.D.: Frames beyond words: applying cluster and sentiment analysis to news coverage of the nuclear power issue. Soc. Sci. Comput. Rev. 34(5), 530–545 (2016)CrossRefGoogle Scholar
  28. 28.
    Cambria, E., Poria, S., Bajpai, R., Schuller, B.: SenticNet 4: a semantic resource for sentiment analysis based on conceptual primitives. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 2666–2677 (2016)Google Scholar
  29. 29.
    Kang, G.J., et al.: Semantic network analysis of vaccine sentiment in online social media. Vaccine 35(29), 3621–3638 (2017)CrossRefGoogle Scholar
  30. 30.
    Doerfel, M.L.: What constitutes semantic network analysis? a comparison of research and methodologies. Connections 21(2), 16–26 (1998)Google Scholar
  31. 31.
    Kharlamov, A.A., Yermolenko, T.V.: Neuronetwork Environment (Neuromorphic Associative Memory) for Information Complexity Overcoming. Searching of Sense in Weak Structured Information Arrays. Part II. Information Processing in Hyppocampus. Informational Technology. 21(11), pp. 883–889 (2015) [in Russian]Google Scholar
  32. 32.
    Orekhov, A.V., Kharlamov, A.A., Bodrunova, S.S.: Network presentation of texts and clustering of messages. In: Proceedings International conference on Internet Science 2019 (INSCI2019), in this volume (2019)CrossRefGoogle Scholar
  33. 33.
    Ore, O.: Theory of Graphs. American Mathematical Society, Providence (1983)zbMATHGoogle Scholar
  34. 34.
    Kharlamov, A.A., Yermolenko, T.V.: Text analysis: linguistics, semantics, pragmatics in the cognitive approach. Int. Sci. J. “Manag. Syst. Mach.” 6(250), 29–33 (2015). [in Ukrainian]Google Scholar
  35. 35.
    Kharlamov, A.A.: Formation of the n-grammatic thematic model of the text. Speech Technol. Number 1–2, 15–23 (2016). [in Russian]Google Scholar
  36. 36.
    Orekhov, A.V.: Markov moment for the agglomerative method of clustering in Euclidean space. Bulletin of Saint Petersburg University, Series Applied Mathematics. Computer Science. Control Processes, 15(1), 76–92 (2019).
  37. 37.
    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
  38. 38.
    Aldenderfer, M.S., Blashfield, R.K.: Cluster Analysis. Sage Publications, Thousand Oaks (1984)CrossRefGoogle Scholar
  39. 39.
    Wald, A.: Sequential Analysis. John Wiley & Sons, Hoboken (1947)zbMATHGoogle Scholar
  40. 40.
    Sirjaev, A.N.: Statistical sequential analysis: optimal stopping rules. Am. Math. Soc. 38, 174 (1973)Google Scholar
  41. 41.
    Orekhov, A.V.: Criterion for estimation of stress-deformed state of SD-materials. AIP Conf. Proc. 1959, 070028 (2018). Scholar
  42. 42.
    Orekhov, A.V.: Approximation-evaluation tests for a stress-strain state of deformable solids. Bull. St. Petersburg Univ. Ser. Appl. Math. Comput. Sci. Control Process. 14(3), 230–242 (2018). Scholar
  43. 43.
    Granichin, O.N., Shalymov, D.S., Avros, R., Volkovich, Z.: A randomized algorithm for finding the number of clusters. Automation and remote control 86–98, (2011). [in Russian]Google Scholar
  44. 44.
    Shalymov, D.S.: Randomized method for determining the number of clusters on a data set. Sci. Tech. Bull. St. Petersburg State Univ. Inf. Technol., Mech. Optics 5(63), 111–116 (2009). [in Russian]Google Scholar
  45. 45.
    Shalymov, D.S.: Algorithms for sustainable clustering based on index functions and stability functions. Stoch. Optimizat. Comput. Sci. 4(1–1), 236–248 (2008). [in Russian]Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

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

Personalised recommendations