Comparison of machine learning methods for sentiment analysis
https://doi.org/10.25205/1818-7900-2024-22-3-49-61
Abstract
Every day the amount of text data containing the subjective evaluation of the author is increasing thanks to the Internet. This information is used, for example, by numerous companies to assess the loyalty of their target audience. Due to the incredibly fast growth of the volume of such texts, their manual processing becomes impractical. It is in such situations that automated sentiment analysis is used, which is an actively developing area of natural language processing. We collected a corpus of medical service reviews, on the basis of which three classifiers were trained. We also performed a
comparative analysis of the obtained results of the models, which belong to traditional or deep machine learning. Our corpus of texts is public and can be useful for other researchers.
About the Authors
M. V. Shvenk
Novosibirsk State University
Russian Federation
Russian Federation
Milana V. Shvenk, Bachelor
Novosibirsk
E. P. Bruches
Novosibirsk State University; A. P. Ershov Institute of Informatics Systems SB RAS
Russian Federation
Russian Federation
Elena P. Bruches, Junior Researcher; Senior Lecturer
Novosibirsk
A. Y. Leman
Novosibirsk State University
Russian Federation
Russian Federation
Anna Y. Leman, Senior Lecturer
Novosibirsk
References
1. Androsov A. Y., Borodaschenko A. Y., Leonidova K. S. Algorithm for determining the tone of media publications to public officials. Izvestia TulSU. Engineering Sciences, 2020, no. 2, pp. 4753. (in Russ.)
2. Ksenofontov G. S. Tonal analysis of economic news. Skif. Student Science Issues, 2022, no. 5 (69), pp. 584–589. (in Russ.)
3. Pazelskaya A. G., Solovyov A. N. The method of determining emotions in texts in Russian. Computer Linguistics and Intelligent Technologies : Proceedings of the International Conference Dialogue’2014. Moscow, Science publ., 2014, pp. 574–586. (in Russ.)
4. Samigulin T. R. Djurabaev A. E. U. Sentiment analysis of text by machine learning methods. Research Result. Information Technologies, 2021, vol. 6, no. 1, pp. 55–62. (in Russ.) DOI: 10.18413/2518-1092-2021-6-1-0-7
5. Peskisheva T. A. Methods for sentiment analysis of natural language texts. Society. Science. Innovations (Scientific and practical conference 2017), 2017, pp. 1730–1742. (in Russ.)
6. Astapov R. L., Dubatov R. S. Classification of texts using convolutional neural networks. Vestnik of Science, 2020, no. 8 (29), pp. 53–56. (in Russ.)
7. Vorobev N. V., Puchkov E. V. Classification of texts using convolutional neural networks. Molodoj issledovatel’ Dona, 2017, no. 6 (9), pp. 2–7. (in Russ.)
8. Bodrunova S. S. Cross-cultural sentiment analysis of user texts on twitter. Vestnik of Moscow University. Series 10. Journalism, 2018, no. 6, pp. 191–212. (in Russ.) DOI: 10.30547/vestnik.journ.6.2018.191212
9. Shunina U. S. Dependence of classification quality on the methods to form a training and test samples. Vestnik UlSTU, 2015, no. 2 (70), pp. 43–46. (in Russ.)
10. Skripachyov V. O., Guyda M. V., Guyda N. V., Zhukov A. O. Features of convolutional neural networks. International Journal of Open Information Technologies, 2022, no. 12, pp. 53–61. (in Russ.)
11. Mayorov D. V. Applying deep learning in predictive input. Scientific Journal, 2023, no. 2 (67), pp. 19–25. (in Russ.)
12. Muhamediyeva D. K., Abdurakhmanova N. N., Mirzayeva N. S. Using conventional neural networks for the problem of text classification. Central Asian Academic Journal of Scientific Research, 2021, no. 1, pp. 213–220.
13. Abinash Tripathy. Sentiment Analysis Using Machine Learning Techniques : dissertation. Department of Computer Science and Engineering National Institute of Technology Rourkela, 2017, p. 131.
14. Borodin A. I., Veynberg R. R., Litvishko O. V. Methods of text processing when creating chatbots. Humanitarian Balkan Studies, 2019, no. 3 (5), pp. 108–111. (in Russ.) DOI: 10.34671/SCH.HBR.2019.0303.0026
15. Saifarov L. S. Using text mining technology in automatic text processing. Economics and Society, 2023, no. 1−2 (104), pp. 639–642. (in Russ.)
16. Berbasov V. D. Comparative review of keras and pytorch neural network libraries. Economics and Society, 2023, no. 8 (111), pp. 423–426. (in Russ.)
17. Vasilchenko A. M. Solving data analysis problems based on machine learning. Universum: Engineering Sciences, 2023, no. 9−1 (114), pp. 50–54. (in Russ.) DOI: 10.32743/UniTech.2023.114.9.15959
18. Shunina U. S., Alekseeva V. A., Klyachkin V. N. Criteria of quality of qualifiers work. Vestnik UlSTU, 2015,no. 2 (70), pp. 67–70. (in Russ.)
19. Bing Liu. Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers, 2012, p. 168.
20. Tkachenko A. L. Solving the problem of university documents classification based on intellectual analysis methods. Vestnik of Cybernetics, 2021, no. 1 (41), pp. 12–19. DOI: 10.34822/1999-7604-2021-1-12-19 (in Russ.)
21. Galchenko Y. V., Nesterov S. A. Sentiment analysis with machine learning methods. SAEC, 2023, no. 3, pp. 369–378. DOI: 10.18720/SPBPU/2/id23-501 (in Russ.)
22. Yurkina A. V., Krutikov A. K. Development of a specialized software module for the formation of a training sample for a neurogoroscope. Universum: Engineering Sciences, 2023, no. 10−1 (115), pp. 61–65. (in Russ.)
23. Hochreiter S., Bengio Y., Frasconi P., Schmidhuber J. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. IEEE Press, 2001, no. 1, p. 15.
24. Pustynnyj I. N. Solving the problem of vanishing gradient using long short term memory neural networks. Innovations and Investments, 2020, no. 2, pp. 130–132. (in Russ.)
Review
For citations:
Shvenk M.V., Bruches E.P., Leman A.Y. Comparison of machine learning methods for sentiment analysis. Vestnik NSU. Series: Information Technologies. 2024;22(3):49-61. (In Russ.) https://doi.org/10.25205/1818-7900-2024-22-3-49-61
Views:
178
Email this article 