METHODOLOGICAL POTENTIAL OF SENTIMENT ANALYSIS: THE CORPUS ASPECT

UDC 81’33

 

Barkovich Aliaksandr Arkad’yevich – DSc (Philology), Associate Professor, Head of the Department of Informatics and Applied Linguistics. Minsk State Linguistic University (21, Zakharova str., 220034, Minsk, Republic of Belarus). E-mail: barkovichaa@gmail.com

Antonov Andrey Vladimirovich – student. Minsk State Linguistic University (21, Zakharova str., 220034, Minsk, Republic of Belarus). E-mail: andrey56735472@gmail.com

 

DOI: https://doi.org/ 10.52065/2520-6729-2023-273-2-5 (In Russian).

 

Key words: : sentiment analysis, text corpus, text tonality, tonal vocabulary, evaluation, context.

 

For citation: Barkovich A. A. Methodological potential of sentiment analysis: the corpus aspect. Proceedings of BSTU, issue 4, Print- and Mediatechnologies, 2023, no. 2 (273), pp. 32–39. DOI: 10.52065/2520-6729-2023-273-2-5 (In Russian).

 

Abstract

This article is devoted to the aspects of the sentiment analysis procedure on the material of a text corpus. Sentiment analysis of text is traditionally focused on the evaluation of small speech artifacts; a typical example of processed text material is a blog or a messenger post. At the same time, the constant development of corpus format considers the implementation of the full range of automated speech processing capabilities in the referential context, including the linguopragmatic in its essence practice of sentiment analysis. These possibilities are in demand, but their full-fledged realization presupposes a preliminary approbation of existing tools of sentiment analysis and their adaptation for conducting research, in particular, in a fully compatible with computer-mediated communication corpus aspect – at the qualitatively innovative level. In the course of the corresponding analysis, the available methodological potential was systematized and characterized, and both ways of tactical actualization and the strategy of improving the practice of sentiment analysis were proposed. The scientific representation of the relevant problems will contribute to the fuller disclosure of the interdisciplinary potential of sentiment analysis and will increase the effectiveness and efficiency of its implementation.

 

Download

References

  1. Mayorova E. V. On sentiment analysis and prospects for its application. Sotsial’nyye i gumanitarnyye nauki. Otechestvennaya i zarubezhnaya literatura [Social and human sciences. Domestic and foreign literature], series 6, Linguistics, 2020, no. 4, pp. 78–87 (In Russian).
  2. Semina T. A. Sentiment analysis: modern approaches and existing problems. Sotsial’nyye i gumanitarnyye nauki. Otechestvennaya i zarubezhnaya literatura [Social and human sciences. Domestic and foreign literature], series 6, Linguistics, 2020, no. 4, pp. 47–64 (In Russian).
  3. Beigi G., Hu X., Maciejewski R., Liu H. An overview of sentiment analysis in social media and its applications in disaster relief. Sentiment analysis and ontology engineering: an environment of computational intelligence / eds. W. Pedrycz, S.-M. Chen, Cham: Springer, 2016, pp. 313–340.
  4. Araque O. Zhu G., Iglesias C. A. A semantic similarity-based perspective of affect lexicons for sentiment analysis. Knowledge-Based Systems, 2019, no. 165, pp. 346–359.
  5. Liu B. Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 2012, vol. 5, no.1, pp. 1–16.
  6. Barkovich A. A., Wang, Q. Linguistic corpora of the Chinese language: a functional aspect. Vestnik MGLU [Bulletin of the MSLU], series 1, Philology, 2015, no. 5 (78), pp. 105–113 (In Russian).
  7. Antonov A. V., Barkovich A. A. Instrument-independent text corpus “Avatar: The Way of Water” (movie reviews). Available at: https://drive.google.com/file/d/1Y7V15sEmH0NI6rAFSbyIjAXd0wYY5h/view (accessed 20.05.2023).
  8. VADER Sentiment Analysis: A Complete Guide, Algo Trading and More. Available at: http://www.multitran.ru (accessed 20.05.2023).
  9. Barkovich A. A. Sentiment Analysis: Linguistic Potential of Preprocessing Regimentation. Virtual’naya kommunikatsiya i sotsial’nyye seti [Virtual Communication and Social Networks], 2023, no. 2(3), pp. 116–123 (In Russian).
  10. Mohammad S. M. Sentiment analysis: Detecting valence, emotions, and other affectual states from text. Emotion measurement, Elsevier, 2016, pp. 201–237.
  11. Pazel’skaya A. G., Solov’ev A. N. A method for determining emotions in texts in Russian. Komp’yuternaya lingvistika i intellektual’nyye tekhnologii: ezhegodnaya Mezhdunarodnaya konferentsiya “Dialog” [Computational Linguistics and Intelligent Technologies: materials of the annual International Conference “Dialogue”], 2011, issue 10, pp. 510–522 (In Russian).
  12. Taboada M., Brooke J., Tofiloski M., Voll K., Stede M. Lexicon-based methods for sentiment analysis. Computational linguistics, 2011, no. 37(2), pp. 267–307.
  13. Kulagin D. I. Open Tonal Dictionary of the Russian Language KartaSlovSent. Komp’yuternaya lingvistika i intellektual’nyye tekhnologii: materialy ezhegodnoy Mezhdunarodnoy konferentsii “Dialog” [Computational Linguistics and Intelligent Technologies: materials of the annual International Conference “Dialogue”], 2021, issue 20, pp. 1106–1119 (In Russian).
  14. Hutto C. J., Gilbert E. VADER: A parsimonious rule-based model for sentiment analysis of social media text. Proceedings of the 8th international conference on weblogs and social media (ICWSM), 2014, May, Ann Arbor, Michigan USA: PKP Publishing Services Network, 2014, pp. 216–225.
  15. Barkovich A. A. Computer-mediated communication: the potential of metalexical significance. Uchenyye zapiski Petrozavodskogo gosudarstvennogo universiteta. Obshchestvennyye i gumanitarnyye nauki [Scientific notes of Petrozavodsk State University. Social and human sciences], 2015, no. 7 (152), pp. 38–43 (In Russian).

26.06.2023