METHODS AND TECHNOLOGIES FOR MEASURING TEXT SENTIMENT
Keywords:
machine learning, logistic regression, text sentiment analysis, TF-IDF, natural language processing, review classification, text vectorization, lemmatization, FlaskAbstract
This article presents a comprehensive comparative analysis of modern machine learning methods used for automated sentiment polarity detection in textual data. Four algorithmic approaches are examined with respect to their functional characteristics, computational complexity, and robustness to lexical and syntactic variations.
Experimental results show that logistic regression combined with stop-word filtering provides the highest accuracy and stability for sentiment classification, offering an optimal balance between computational efficiency and prediction quality.
The approach is characterized by low resource consumption, high interpretability, and ease of integration into applied systems.
References
1. Choosing the Best Machine Learning Classification Model and Avoiding Overfitting
2. [Электронный ресурс]. – MathWorks, 2025. – URL:
3. https://www.mathworks.com/campaigns/offers/next/choosing-the-best-machine-learning-classification-model-and-avoiding-overfitting.html (дата обращения: 27.09.2025 22:04).
4. Лемматизация [Электронный ресурс] // Wikipedia. – URL:
5. https://ru.wikipedia.org/wiki/Лемматизация (дата обращения: 28.09.2025 11:14).
6. Jurafsky D. Speech and Language Processing [Электронный ресурс]: 3rd ed., draft / D. Jurafsky, J. H. Martin. – Stanford University, 2023. – URL: https://web.stanford.edu/~jurafsky/slp3/ (дата обращения: 14.10.2025 16:20).
7. Pedregosa F. Scikit-learn: Machine Learning in Python / F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel [и др.] // Journal of Machine Learning Research. – 2011. – Т. 12. – С. 2825–2830. – URL: https://jmlr.org/papers/v12/pedregosa11a.html (дата обращения: 14.10.2025 16:20).
8. Raschka S. Python Machine Learning: 4th ed. / S. Raschka, V. Mirjalili. – Packt Publishing, 2022. – URL: https://sebastianraschka.com/books.html (дата обращения: 14.10.2025 16:20).
9. Manning C. D. Introduction to Information Retrieval / C. D. Manning, P. Raghavan, H. Schütze. – Cambridge: Cambridge University Press, 2008. – DOI: 10.1017/CBO9780511809071. – URL: https://nlp.stanford.edu/IR-book/ (дата обращения: 14.10.2025 16:20).
10. Bird S. Natural Language Processing with Python / S. Bird, E. Klein, E. Loper. – O’Reilly Media, 2009. – URL: https://www.nltk.org/book/ (дата обращения: 14.10.2025 16:20).
11. Zhang L. Deep Learning for Sentiment Analysis: A Survey / L. Zhang, S. Wang, B. Liu // Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. – 2018. – Vol. 8, No. 4. – e1253. – DOI: 10.1002/widm.1253 (дата обращения: 14.10.2025 16:20).
12. Kowsari K. Text Classification Algorithms: A Survey / K. Kowsari, K. J. Meimandi, M. Heidarysafa, S. Mendu, L. Barnes, D. E. Brown // Information. – 2019. – Vol. 10, No. 4. – 150. – DOI: 10.3390/info10040150 (дата обращения: 14.10.2025 16:20).
13. Корякин, С. В. Разработка универсальной среды проектирования автоматизированных систем защищенного исполнения / С. В. Корякин // Проблемы автоматики и управления. – 2021. – № 2(41). – С. 40 – 55. – EDN EFUUDC.
14. Корякин, С. В. Разработка концепции построения программно-аппаратного ядра универсальной среды проектирования автоматизированных систем защищенного исполнения / С. В. Корякин // Проблемы автоматики и управления. – 2020. – № 1(38). – С. 60–69. – DOI 10.5281/zenodo.3904117. – EDN IWZQBP.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 А.Б. Райимкулов, М.Ж. Ашералиева, Ю.С. Корякина, С.В. Корякин
This work is licensed under a Creative Commons Attribution 4.0 International License.
