Aspect-Based Sentiment Analysis of Political Discourse

Tyumen State University Herald. Humanities Research. Humanitates


2021, Vol. 7. № 3 (27)

Aspect-Based Sentiment Analysis of Political Discourse

For citation: Brunova E. G., Bidulya Yu. V., Gorbunov A. A. 2021. “Aspect-Based Sentiment Analysis of Political Discourse”. Tyumen State University Herald. Humanities Research. Humanitates, vol. 7, no. 3 (27), pp. 6-22. DOI: 10.21684/2411-197X-2021-7-3-6-22

About the authors:

Elena G. Brunova, Dr. Sci. (Philol.), Professor, Department of the English Language, Military Historian, University of Tyumen;; ORCID: 0000-0002-8493-5932

Yulia V. Bidulya, Cand. Sci. (Philol.), Associate Professor, Department of Information Systems, University of Tyumen;; ORCID: 0000-0003-1878-3114

Alexander A. Gorbunov, Master’s degree student, University of Tyumen;


The existing systems for accurate sentiment analysis are mainly based on statistical and mathematical principles. However, more promising are the works that are devoted to the study of the linguistic features of the evaluation expression. The results of this formalization can be applied both in the field of affective computing for further improvement of automatic systems and for linguistics and related sciences.

The novelty of this study lies mainly in the development of an algorithm based on the identified linguistic rules. In addition, the research material is political discourse, which has not yet been studied enough by specialists of affective computing. The relevance of this work is justified by the growing need for categorization of information published on the Internet.

The purpose of the study is to develop a system for machine sentiment analysis of English-language political texts, as well as to identify aspects and their distribution for subsequent use in enhancement. The article discusses the linguistic features of sentiment analysis and suggests a classification of linguistic units with sentiment potential in relation to levels of language structure. The results of an experiment on testing the operation of the sentiment analysis system, conducted on 300 news articles and user comments taken from, are also presented. The accuracy of the system is 92%. In addition, the selected 40 comments were manually marked up and tagged; during this process the expert identified 25 aspects. Furthermore, 3 formal patterns were identified in the distribution of aspect terms, which is necessary for creating an automatic system. The first peculiarity is that the aspect terms are repeated in two consecutive sentences. The second is that aspect terms are often the themes of sentences. Finally, the third — a high frequency of distribution of aspect terms at the beginning and end of the text (document) was revealed.


  1. Brunova E. G., Bidulya Yu. V. 2017. “The сustomer is always right: sentiment analysis for bank service quality”. Tyumen State University Herald. Humanities Research. Humanitates, vol. 3, no. 1, pp. 72-89. [In Russian]

  2. Van Dijk T. A. 2013. Discourse and Power: Representation of Domination in Language and Communication. Moscow: LIBROKOM. 344 p. [In Russian]

  3. Komissarova N. G., Jakupova D. R. 2018. “Evaluation in the media discourse”. Philological Sciences. Questions of Theory and Practice, no. 2-1 (80), pp. 83-87. [In Russian]

  4. Maryanchik V. A. 2011. “Evaluativity as a text category”. Northern (Arctic) Federal University Herald. Series: Humanities and Social Sciences, no. 1, pp. 100-103. [In Russian]

  5. Papina A. F. 2002. Text: Its Units and Global Categories. Moscow: URSS. 367 p. [In Russian]

  6. Chudinov A. P. 2001. Russia in a Metaphorical Mirror: Cognitive Research of Political Metaphor (1991-2000): monography. 238 p. [In Russian]

  7. Shejgal E. I. 2005. Semiotics of Political Discourse. Moscow: RGB. 431 p. [In Russian]

  8. Bhatt A. et al. 2015. “Amazon review classification and sentiment analysis”. International Journal of Computer Science and Information Technologies, vol. 6, no. 6, pp. 5107-5110.

  9. Blinov P. D., Kotelnikov E. V. 2015. Semantic Similarity for Aspect-Based Sentiment Analysis. Computational Linguistics and Intellectual Technologies: Proceedings of the Annual International Conference “Dialogue”. Edited by V. P. Selegey. Мoscow: RSUH. Iss. 14, pp. 12-22.

  10. Cambria E. 2016. “Affective computing and sentiment analysis”. IEEE Intelligent Systems, vol. 31, no. 2, pp. 102-107.

  11. Emotion classification using NRC Lexicon in Python. 2020. Accessed on 23 May 2021.

  12. Fang X., Zhan J. 2015. “Sentiment analysis using product review data”. Journal of Big Data, vol. 2, no. 1, pp. 1-14.

  13. Fellbaum C. 1998. WordNet: An Electronic Lexical Database. Cambridge, MA: MIT Press. 499 p.

  14. Gold D. et al. 2018. “Corpus of aspect-based sentiment in political debates”. Proceedings of the 14th Conference on Natural Language Processing (KONVENS 2018). Vienne. Pp. 89-99.

  15. Haselmayer M., Jenny M. 2017. “Sentiment analysis of political communication: combining a dictionary approach with crowdcoding”. Quality and Quantity, no. 51, pp. 2623-2646.

  16. Hatzivassiloglou V., McKeown K. 1997. “Predicting the semantic orientation of adjectives”. Proceedings of the 35th Annual Meeting of ACL. Madrid. Pp. 174-181.

  17. Lin C., He Y. 2009. “Joint sentiment/topic model for sentiment analysis”. Proceedings of the 18th ACM Conference on Information and Knowledge Management. Pp. 375-384.

  18. Mayorov V., Andrianov I., Astrakhantsev N., Avanesov V., Kozlov I., Turdakov D. (ed.). 2015. “A high precision method for aspect extraction in Russian”. Computational Linguistics and Intellectual Technologies: Proceedings of the Annual International Conference “Dialogue”. Edited by V. P. Selegey. Мoscow: RSUH. Iss. 14, pp. 34-44.

  19. Miller G. A. 1995. WordNet: A Lexical Database for English.

  20. Minsky M. 2006. “The emotion machine: commonsense thinking”. Artificial Intelligence, and the Future of the Human Mind. Simon and Schuster. 400 p.

  21. Mittal A., Goel A. 2012. “Stock prediction using twitter sentiment analysis”. CS229: Machine Learning. Standford University Course, vol. 15. Accessed on 23 May 2021. http://cs229.

  22. Mukherjee S., Bhattacharyya P. 2012. “Feature specific sentiment analysis for product reviews”. International Conference on Intelligent Text Processing and Computational Linguistics. Springer, Berlin, Heidelberg. Pp. 475-487.

  23. Mullen T., Malouf R. 2006. “A Preliminary Investigation into Sentiment Analysis of Informal Political Discourse”. AAAI Spring Symposium: Computational Approaches to Analyzing Weblogs. Pp. 159-162.

  24. Neidhardt J., Rümmele N., Werthner H. 2017. “Predicting happiness: user interactions and sentiment analysis in an online travel forum”. Information Technology and Tourism, vol. 17, no. 1, pp. 101-119.

  25. Poria S., Cambria E., Howard N., Huang G.-B., Hussain A. 2016. “Fusing audio, visual and textual clues for sentiment analysis from multimodal content”. Neurocomputing, no. 174, pp. 50-59.

  26. Accessed on 23 May 2021.

  27. Spencer J., Uchyigit G. 2012. “Sentimentor: sentiment analysis of twitter data”. SDAD@ ECML/PKDD. Pp. 56-66.

  28. Vasilyev V. G., Denisenko A. A., Solovyev D. A. 2015. Aspect Extraction and Twitter Sentiment Classification by Fragment Rules. Computational Linguistics and Intellectual Technologies: Proceedings of the Annual International Conference “Dialogue”. Edited by V. P. Selegey. Мoscow: RSUH. Iss. 14, pp. 76-88.

  29. Wang X. et al. 2011. “Topic sentiment analysis in twitter: a graph-based hashtag sentiment classification approach”. Proceedings of the 20th ACM International Conference on Information and Knowledge Management. Pp. 1031-1040.