Aim is to describe the features of the expression of opinion in analytical articles on politics. Methodology. The language and the arrangement of the text main components expressing opinion, were analyzed, the interaction of sentiment and counterfactual values, characteristics of referring to someone else’s opinion have been considered, as well as the way to find the author’s opinion using the words that are rare for a collection of documents. Results. Identification of lexical and grammatical features used to express opinion in political media discourse. Research implications. Suggestions for using these characteristics in identifying opinions.

sentiment analysis, opinion, modality, direct speech, opinion mining

1. Belyakov M. V., Maksimenko O. I. [Pragmatics of metaphor in Russian diplomatic discourse]. In: Borisova A. S., Ignatenko A. V., Larina T. V., Lomakina O. V., eds. IV Firsovskie chteniya. Yazyk v sovremennykh diskursivnykh praktikakh: materialy dokladov i soobshchenii Mezhdunarodnoi nauchno-prakticheskoi konferentsii, Moskva, 22–23 oktyabrya 2019 g. [IV Firsov readings. Language in modern discourse practices: proceedings of the International scientific and practical conference, Moscow, October 22nd–23rd, 2019]. Moscow, Peoples’ Friendship University of Russia Publ., 2019, pp. 453–459.
2. Semina T. A. [Author’s opinion mining using inverse document frequency]. In: Vestnik Moskovskogo gosudarstvennogo oblastnogo universiteta (elektronnyi zhurnal) [Bulletin of Moscow Region State University (e-journal)], 2019, no. 2. Available at: www.evestnik-mgou.ru (accessed: 04.10.2019).
3. Yusupov I. [Named entity recognition using syntactic and semantic features and neural networks]. In: Dialog: Trudy mezhdunarodnoi konferentsii po komp’yuternoi lingvistike i intellektual’nym tekhnologiyam, Moskva, 1–4 iyunya 2016 g.) [Dialogue: Proceedings of the international conference on computational linguistics and intellectual technologies, Moscow, June 1st–4th, 2016], vol. 15 (22). Available at: http://www.dialog-21.ru/media/3475/yusupov.pdf (accessed: 04.10.2019).
4. Baymurzina D. R., Kuznetsov D. P., Burtsev M. S. Language model embeddings improve sentiment analysis in Russian. In: Komp’yuternaya lingvistika i intellektual’nye tekhnologii: po materialam ezhegodnoi mezhdunarodnoi konferentsii «Dialog», Moskva, 29 maya – 1 iyunya 2019 g. [Computational linguistics and intellectual technologies: Based on the materials of the annual international conference “Dialogue”, Moscow, May 29th – June 1st, 2019]. Moscow, Russian State Humanitarian University Publishing, 2019, pp. 53–62.
5. Chiranjeevi P., Santosh D. T., Vishnuvardhan B. Survey on Sentiment Analysis Methods for Reputation Evaluation. In: Cognitive Informatics and Soft Computing. Singapore, Springer, 2019, pp. 53–66.
6. Choi Y., Wiebe J., Mihalcea R. Coarse-grained +/– Effect Word Sense Disambiguation for Implicit Sentiment Analysis. In: The IEEE Transactions on Affective Computing, 2017, vol. 8, no. 4, pp. 471–479.
7. Li X., Wu C., Mai F. The effect of online reviews on product sales: A joint sentiment-topic analysis. In: Information & Management, 2019, vol. 56, no. 2, pp. 172–184.
8. Rusnachenko N., Loukachevitch N. V. Extracting Sentiment Attitudes from Analytical Texts via Piecewise Convolutional Neural Network. In: DAMDID/RCDL, October 9th–12th, 2018. Мoscow, 2018, pp. 186–192.
9. Saura J. R., Palos-Sanchez P., Grilo A. Detecting indicators for startup business success: Sentiment analysis using text data mining. In: Sustainability, 2019, vol. 11, no. 3. Available at: https://www.mdpi.com/2071-1050/11/3/917 (accessed: 04.10.2019).
10. Zhang L., Liu B. Identifying noun product features that imply opinions. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Vol. 2. Shoumen, Bulgaria, Association for Computational Linguistics, 2011, pp. 575–580.