kaz44Вестник Университета Шакарима. Серия технические наукиBulletin of Shakarim University. Technical Sciences2788-79953006-0524«Шәкәрім университеті» КеАҚ10.53360/2788-7995-2023-1(9)-8kaz44-418Research ArticleСТАТЬИОБЗОР МЕТОДОВ ОПРЕДЕЛЕНИЯ ТОНАЛЬНОСТИ ТЕКСТОВ НА ЕСТЕСТВЕННЫХ ЯЗЫКАХREVIEW OF METHODS FOR DETERMINING THE TONATION OF TEXTS IN NATURAL LANGUAGESНурсакитовК. Е.NursakitovK.

докторант «школы информационных технологий и интеллектуальных систем»,

070004, г. Усть-Каменогорск, ул. Протозанова А.К., 69

doctoral student of the "School of Information Technologies and Intelligent Systems",

070004, Ust-Kamenogorsk, 69 Protozanov Street

nursakitov@bk.ruБекишевА. Т.BekishevA.

докторант «школы информационных технологий и интеллектуальных систем», 

070004, г. Усть-Каменогорск, ул. Протозанова А.К., 69

doctoral student of the "School of Information Technologies and Intelligent Systems",

070004, Ust-Kamenogorsk, 69 Protozanov Street

bekishev@bk.ruКумаргажановаС. К.KumargazhanovaS.

кандидат технических наук: декан «школы информационных технологий и интеллектуальных систем»,

070004, г. Усть-Каменогорск, ул. Протозанова А.К., 69

Candidate of Technical Sciences: Dean of the "School of Information Technologies and Intelligent Systems",

070004, Ust-Kamenogorsk, 69 Protozanov Street

skumargazhanova@gmail.comУркумбаеваА. М.UrkumbaevaA.

кандидат технических наук, старший преподаватель «школы информационных технологий и интеллектуальных систем»,

070004, г. Усть-Каменогорск, ул. Протозанова А.К., 69

Candidate of Technical Sciences, Senior Lecturer of the "School of Information Technologies and Intelligent Systems",

070004, Ust-Kamenogorsk, 69 Protozanov Street

urkumbaeva@mail.ruВосточно-Казахстанский технический университет имени Д.СерикбаеваКазахстанD. Serikbayev East Kazakhstan technical universityKazakhstan20233103202301(9)5766Copyright © Нурсакитов К.Е., Бекишев А.Т., Кумаргажанова С.К., Уркумбаева А.М., 20232023Нурсакитов К.Е., Бекишев А.Т., Кумаргажанова С.К., Уркумбаева А.М.Nursakitov K., Bekishev A., Kumargazhanova S., Urkumbaeva A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://tech.vestnik.shakarim.kz/jour/article/view/418

Анализ настроений в комментариях пользователей находит применение во многих областях, таких как оценка качества товаров и услуг, анализ эмоций в сообщениях, обнаружение фишинговой рекламы. Существует множество методов анализа тональности текстовых данных на русском языке, но автоматический анализ тональности русскоязычных текстов разработан гораздо меньше, чем для других основных языков мира. Данная статья является частью более широкого исследования по созданию информационной системы обнаружения опасного контента в киберпространстве Казахстана. Цель данной статьи – дать аналитический обзор различных подходов к анализу тональности русскоязычных текстов и сравнить современные методы решения задачи классификации текстов. Кроме того, в статье ставится задача выявить тенденции развития в этой области и выбрать оптимальные алгоритмы для использования в дальнейших исследованиях. Обзор охватывает различные методы предварительной обработки текстовых данных, векторизации и машинной классификации для анализа тональности текстов и завершается анализом существующих баз данных по этой теме. В статье обозначены некоторые из основных нерешенных проблем при анализе тональности русскоязычных текстов и обсуждаются планируемые дальнейшие исследования. 

The analysis of sentiment in user comments finds application in many areas, such as evaluating the quality of goods and services, analyzing emotions in messages, and detecting phishing advertisements. There are numerous methods for analyzing the sentiment of textual data in the Russian language, but automatic sentiment analysis of Russian-language texts is much less developed than for other major world languages. This article is part of a broader study on the creation of an information system for detecting dangerous content in the cyberspace of Kazakhstan. The purpose of this article is to provide an analytical review of the different approaches to sentiment analysis of Russian-language texts and to compare modern methods for solving the problem of text classification. Additionally, the article seeks to identify development trends in this area and select the best algorithms for use in further research. The review covers different methods for text data preprocessing, vectorization, and machine classification for sentiment analysis of texts, and it concludes with an analysis of existing databases on this topic. The article identifies some of the main unresolved problems in sentiment analysis of Russianlanguage texts and discusses planned further research. 

машинное обучениерекуррентные нейронные сетиобработка естественного языкатональность текстаmachine learningrecurrent neural networksnatural language processingtext sentimentNLPinformation TechnologyReferencesEnikolopov S.N., Kuznetsova Y.M., Smirnov I.V., Stankevich M.A., Chudova N.V. Creating a text analysis tool for socio-humanitarian research. Part 1. Methodical and methodological aspects. Artificial Intelligence and Decision Making. – 2019. – no. 2, pp. 28-38. doi:10.14357/20718594190203. (In Russian).Enikolopov S.N., Kuznetsova Y.M., Smirnov I.V., Stankevich M.A., Chudova N.V. Creating a text analysis tool for socio-humanitarian research. Part 1. Methodical and methodological aspects. Artificial Intelligence and Decision Making. – 2019. – no. 2, pp. 28-38. doi:10.14357/20718594190203. (In Russian).Polyakov E. V., Voskov L. S., Abramov P. S., Polyakov S. V. Generalized approach to sentiment analysis of short text messages in natural language processing. Informatsionno-upravliaiushchie sistemy [Information and Control Systems], 2020, no. 1, pp. 2–14. doi:10.31799/1684-8853-2020-1-2-14. (In Russian).Polyakov E. V., Voskov L. S., Abramov P. S., Polyakov S. V. Generalized approach to sentiment analysis of short text messages in natural language processing. Informatsionno-upravliaiushchie sistemy [Information and Control Systems], 2020, no. 1, pp. 2–14. doi:10.31799/1684- 8853-2020-1-2-14. (In Russian).Soumya G. K., Joseph S. Text classification by augmenting bag of words (BOW) representation with co-occurrence feature. IOSR Journal of Computer Engineering, 2014, vol. 16(1), pp. 34-38.Soumya G. K., Joseph S. Text classification by augmenting bag of words (BOW) representation with co-occurrence feature. IOSR Journal of Computer Engineering, 2014, vol. 16(1), pp. 34-38.Potdar K., Pardawala T. S., Pai C. D. A comparative study of categorical variable encoding techniques for neural network classifiers. International Journal of Computer Applications, 2017, vol. 175, no. 4, pp. 7–9.Potdar K., Pardawala T. S., Pai C. D. A comparative study of categorical variable encoding techniques for neural network classifiers. International Journal of Computer Applications, 2017, vol. 175, no. 4, pp. 7–9.Steinberger J., Jezek K. Text summarization and singular value decomposition Proceedings of International Conference on Advances in Information Systems, Springer, Berlin, Heidelberg, 2004, pp. 245-254.Steinberger J., Jezek K. Text summarization and singular value decomposition Proceedings of International Conference on Advances in Information Systems, Springer, Berlin, Heidelberg, 2004, pp. 245-254.Mikolov T., Chen K., Corrado G., Dean J. Efficient estimation of word representations in vector space. Proceedings of the International Conference on Learning Representations (ICLR 2013), 2013. Available at: https://openreview.net/forum?id=idpCdOWtqXd60#7b076554-87ba-4e1e-b7cc2ac107ce8e4d (accessed 2 May 2020).Mikolov T., Chen K., Corrado G., Dean J. Efficient estimation of word representations in vector space. Proceedings of the International Conference on Learning Representations (ICLR 2013), 2013. Available at: https://openreview.net/forum?ididpCdOWtqXd60#7b076554-87ba-4e1e-b7cc2ac107ce8e4d (accessed 2 May 2020).Pennington J., Socher R., Manning C. D. Glove: Global vectors for word representation. Proceedings of International Conference on Empirical Methods in Natural Language Processing (EMNLP-2014), 2014, pp. 1532-1543.Pennington J., Socher R., Manning C. D. Glove: Global vectors for word representation. Proceedings of International Conference on Empirical Methods in Natural Language Processing (EMNLP-2014), 2014, pp. 1532-1543.Pylieva H., Chernodub A., Grabar N., Hamon T. Improving automatic categorization of technical vs. Laymen medical words using fasttext word embeddings. Proceedings of the 1st International Workshop on Informatics and Data-Driven Medicine, IDDM 2018, 2018, pp. 93–102.Pylieva H., Chernodub A., Grabar N., Hamon T. Improving automatic categorization of technical vs. Laymen medical words using fasttext word embeddings. Proceedings of the 1st International Workshop on Informatics and Data-Driven Medicine, IDDM 2018, 2018, pp. 93–102.Devlin J., Chang M., Lee K., Toutanova K. Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 2019, vol. 1 (Long and Short Papers), pp. 4171-4186. doi:10.18653/v1/N19-1423Devlin J., Chang M., Lee K., Toutanova K. Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 2019, vol. 1 (Long and Short Papers), pp. 4171-4186. doi:10.18653/v1/N19-1423Sanh V., Debut L., Chaumond J., Wolf T. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (accessed 05 April 2020).Sanh V., Debut L., Chaumond J., Wolf T. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (accessed 05 April 2020).Kuratov Yu., Arkhipov M. Adaptation of deep bidirectional multilingual transformers for russian language. Computational Linguistics and Intellectual Technologies, 2019, iss. 18, pp. 333-339 (In Russian).Kuratov Yu., Arkhipov M. Adaptation of deep bidirectional multilingual transformers for russian language. Computational Linguistics and Intellectual Technologies, 2019, iss. 18, pp. 333-339 (In Russian).Peters M., Neumann M., Iyyer M., Gardner M., Clark C., Lee K., Zettlemoyer L. Deep contextualized word representations. NAACL-HLT. – 2018, vol. 1 (Long Papers). – pp. 2227-2237. doi:10.18653/v1/N18-1202Peters M., Neumann M., Iyyer M., Gardner M., Clark C., Lee K., Zettlemoyer L. Deep contextualized word representations. NAACL-HLT. – 2018, vol. 1 (Long Papers). – pp. 2227-2237. doi:10.18653/v1/N18-1202Dvoynikova A., Verkholyak O., Karpov A. Analytical review of methods for identifying emotions in text data. CEUR-WS, 2020. – vol. 2552. – pp. 8-21.Dvoynikova A., Verkholyak O., Karpov A. Analytical review of methods for identifying emotions in text data. CEUR-WS, 2020. – vol. 2552. – pp. 8-21.Tutubalina Е. V., Ivanov V. V., Zagulova М. А., Mingazov N. R., Alimova I. S., Malykh V. А. Sentiment classification of reviews and twitter posts based on dictionaries. Russian Digital Libraries Journal, 2015, vol. 18, no. 3-4, pp. 138–162. (In Russian).Tutubalina Е. V., Ivanov V. V., Zagulova М. А., Mingazov N. R., Alimova I. S., Malykh V. А. Sentiment classification of reviews and twitter posts based on dictionaries. Russian Digital Libraries Journal, 2015, vol. 18, no. 3-4, pp. 138–162. (In Russian).Panicheva P. V. ATEX: a rule-based sentiment analysis system processing texts in various topics. Computational Linguistics and Intellectual Technologies, 2013, iss. 12, vol. 2, pp. 101-113 (In Russian).Panicheva P. V. ATEX: a rule-based sentiment analysis system processing texts in various topics. Computational Linguistics and Intellectual Technologies, 2013, iss. 12, vol. 2, pp. 101-113 (In Russian).Kotelnikov E. V., Klekovkina M. V. Automatic text tonality analysis based on machine learning methods. Computational Linguistics and Intellectual Technologies, 2012. – iss. 11, vol. 2. – pp. 27- 36. (In Russian).Kotelnikov E. V., Klekovkina M. V. Automatic text tonality analysis based on machine learning methods. Computational Linguistics and Intellectual Technologies, 2012. – iss. 11, vol. 2. – pp. 27- 36. (In Russian).Maltseva A.V., Makhnytkina O.V., Shilkina N.E., Lizunova I.A. Social media sentiment analysis with context space model. Communications in Computer and Information Science, 2020. – vol. 1135, pp. 399-412. doi:10.1007/978-3-030-39296-3_29.Maltseva A.V., Makhnytkina O.V., Shilkina N.E., Lizunova I.A. Social media sentiment analysis with context space model. Communications in Computer and Information Science, 2020. – vol. 1135, pp. 399-412. doi:10.1007/978-3-030-39296-3_29.Aken B., Risch J., Krestel R., Loser A. Challenges for toxic comment classification: An in-depth error analysis. EMNLP, 2018. – pp. 33-42.Aken B., Risch J., Krestel R., Loser A. Challenges for toxic comment classification: An in-depth error analysis. EMNLP, 2018. – pp. 33-42.Voronina I.E., Goncharov V.A. Analysis of the emotional color of messages in social networks (for example, the “Vkontakte network”). Bulletin of the Voronezh State University. Series: System Analysis and Information Technologies. – 2015. – no. 4. – pp. 151-158. (In Russian).Voronina I.E., Goncharov V.A. Analysis of the emotional color of messages in social networks (for example, the “Vkontakte network”). Bulletin of the Voronezh State University. Series: System Analysis and Information Technologies. – 2015. – no. 4. – pp. 151-158. (In Russian).Konig A.C., Brill E. Reducing the human overhead in text categorization. Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. – 2006. – pp. 598-603.Konig A.C., Brill E. Reducing the human overhead in text categorization. Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. – 2006. – pp. 598-603.Lakshmi B.S., Raj P.S., Vikram R.R. Sentiment analysis using deep learning technique CNN with KMeans. International Journal of Pure and Applied Mathematics. – 2017. – vol. 114, no. 11. – pp. 47-57.Lakshmi B.S., Raj P.S., Vikram R.R. Sentiment analysis using deep learning technique CNN with KMeans. International Journal of Pure and Applied Mathematics. – 2017. – vol. 114, no. 11. – pp. 47-57.Kulagin D.I. Otkrytyj tonal'nyj slovar' russkogo yazyka KartaSlovSent // Komp'yuternaya lingvistika i intellektual'nye tekhnologii: materialy ezhegodnoj Mezhdunarodnoj konferencii «Dialog. – 2021. – №. 20. – S. 1106-1119.Kulagin D.I. Otkrytyj tonal'nyj slovar' russkogo yazyka KartaSlovSent // Komp'yuternaya lingvistika i intellektual'nye tekhnologii: materialy ezhegodnoj Mezhdunarodnoj konferencii «Dialog. – 2021. – №. 20. – S. 1106-1119.Loukachevitch N., Levchik A. Creating a general Russian sentiment lexicon. Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC’16). – 2016. – pp. 1171-1176.Loukachevitch N., Levchik A. Creating a general Russian sentiment lexicon. Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC’16). – 2016. – pp. 1171-1176.Loukachevitch N., Dobrov B. RuThes linguistic ontology vs. Russian wordnets. Proceedings of the 7th Global Wordnet Conference. – 2014. – pp. 154-162.Loukachevitch N., Dobrov B. RuThes linguistic ontology vs. Russian wordnets. Proceedings of the 7th Global Wordnet Conference. – 2014. – pp. 154-162.Alexeeva S., Kolcov S., Koltsova O. Linis-crowd.org: A lexical resource for Russian sentiment analysis of social media. Trudy XVIII ob”edinennoj konferencii «Internet i sovremennoe obshchestvo» (IMS-2015) [Proceedings of the XVIII Joint Conference “Internet and Modern Society” (IMS2015)]. – 2015. – pp. 25-34. (In Russian).Alexeeva S., Kolcov S., Koltsova O. Linis-crowd.org: A lexical resource for Russian sentiment analysis of social media. Trudy XVIII ob”edinennoj konferencii «Internet i sovremennoe obshchestvo» (IMS-2015) [Proceedings of the XVIII Joint Conference “Internet and Modern Society” (IMS2015)]. – 2015. – pp. 25-34. (In Russian).Sokolova M., Bobicev V. Classification of emotion words in Russian and Romanian languages. Proceedings of the International Conference RANLP-2009. – 2009. – pp. 416-420.Sokolova M., Bobicev V. Classification of emotion words in Russian and Romanian languages. Proceedings of the International Conference RANLP-2009. – 2009. – pp. 416-420.Belyakov M.V. The analysis of news messages on the RF ministry of foreign affairs affairs website by the sentimental analysis (article 2). Bulletin of the Peoples’ Friendship University of Russia. Series: Theory of Language. Semiotics. Semantics. – 2016. – no. 4. – pp. 115-124. (In Russian).Belyakov M.V. The analysis of news messages on the RF ministry of foreign affairs affairs website by the sentimental analysis (article 2). Bulletin of the Peoples’ Friendship University of Russia. Series: Theory of Language. Semiotics. Semantics. – 2016. – no. 4. – pp. 115-124. (In Russian).Loukachevitch N., Blinov P., Kotelnikov E., Rubtsova Y., Ivanov V., Tutubalina E. SentiRuEval: testing object-oriented sentiment analysis systems in Russian. Computational Linguistics and Intellectual Technologies. – 2015. – iss. 14, vol. 2. – pp. 3-13.Loukachevitch N., Blinov P., Kotelnikov E., Rubtsova Y., Ivanov V., Tutubalina E. SentiRuEval: testing object-oriented sentiment analysis systems in Russian. Computational Linguistics and Intellectual Technologies. – 2015. – iss. 14, vol. 2. – pp. 3-13.Lukashevich N.V., Rubtsova Y. V. SentiRuEval-2016: overcoming time gap and data sparsity in tweet sentiment analysis. Computational Linguistics and Intellectual Technologies. – 2016. – iss. 15. – pp. 416-426.Lukashevich N.V., Rubtsova Y. V. SentiRuEval-2016: overcoming time gap and data sparsity in tweet sentiment analysis. Computational Linguistics and Intellectual Technologies. – 2016. – iss. 15. – pp. 416-426.Rubcova U.V. Building a text corpus for setting up a tone classifier. Software & Systems. – 2015. – no. 1(109), pp. 72–78. (In Russian).Rubcova U.V. Building a text corpus for setting up a tone classifier. Software & Systems. – 2015. – no. 1(109), pp. 72–78. (In Russian).Chetviorkin I., Braslavskiy P., Loukachevich N. Sentiment analysis track at ROMIP 2011. Computational Linguistics and Intellectual Technologies. – 2012. – iss. 11, vol. 2. – pp. 1-14.Chetviorkin I., Braslavskiy P., Loukachevich N. Sentiment analysis track at ROMIP 2011. Computational Linguistics and Intellectual Technologies. – 2012. – iss. 11, vol. 2. – pp. 1-14.Glazkova A.V. The evaluation of the proximity of text categories for solving electronic documents classification tasks. Bulletin of Tomsk State University. Management, Computer Engineering and Informatics. – 2015, no. 2(31). – pp. 18-25. doi:10.17223/19988605/31/2. (In Russian).Glazkova A.V. The evaluation of the proximity of text categories for solving electronic documents classification tasks. Bulletin of Tomsk State University. Management, Computer Engineering and Informatics. – 2015, no. 2(31). – pp. 18-25. doi:10.17223/19988605/31/2. (In Russian).Perepelkina O., Kazimirova E., Konstantinova M. RAMAS: Russian multimodal corpus of dyadic interaction for affective computing. Proceedings of 20th International Conference on Speech and Computer SPECOM-2018, Springer, Cham. – 2018. – pp. 501-510.Perepelkina O., Kazimirova E., Konstantinova M. RAMAS: Russian multimodal corpus of dyadic interaction for affective computing. Proceedings of 20th International Conference on Speech and Computer SPECOM-2018, Springer, Cham. – 2018. – pp. 501-510.Zafar L., Afzal M.T., Ahmed U. Exploiting polarity features for developing sentiment analysis tool. CEUR-WS, 2017, vol. 1874, no. 4. Available at: http://ceur-ws.org/Vol1874/paper_4.pdf (accessed 2 May 2020).Zafar L., Afzal M.T., Ahmed U. Exploiting polarity features for developing sentiment analysis tool. CEUR-WS, 2017, vol. 1874, no. 4. Available at: http://ceur-ws.org/Vol1874/paper_4.pdf (accessed 2 May 2020).Zvereva P. Sentiment-analysis of text (texts about Russia and the Russians from The New York Times). Bulletin of the Moscow State Regional University. Series: Linguistics. – 2014. – no. 5. – pp. 32-37. (In Russian).Zvereva P. Sentiment-analysis of text (texts about Russia and the Russians from The New York Times). Bulletin of the Moscow State Regional University. Series: Linguistics. – 2014. – no. 5. – pp. 32-37. (In Russian).Krivonogova S.A. Psychoemotional color of the text: theory and research methods. Materialy 68-j nauchnoj konferencii «Nauka YUURGU» [Materials of the 68th Scientific Conference “Science of the South Ural State University”]. – 2016. – vol. 100. – pp. 368–375. (In Russian).Krivonogova S.A. Psychoemotional color of the text: theory and research methods. Materialy 68-j nauchnoj konferencii «Nauka YUURGU» [Materials of the 68th Scientific Conference “Science of the South Ural State University”]. – 2016. – vol. 100. – pp. 368–375. (In Russian).Thelwall M. The heart and soul of the web? Sentiment strength detection in the social web with SentiStrength. Cyberemotions, Springer, Cham. – 2017. – pp. 119-134.Thelwall M. The heart and soul of the web? Sentiment strength detection in the social web with SentiStrength. Cyberemotions, Springer, Cham. – 2017. – pp. 119-134.Mayorov V., Andrianov I. MayAnd at SemEval-2016 Task 5: Syntactic and word2vec-based approach to aspect-based polarity detection in Russian. Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). – 2016. – pp. 325-329.Mayorov V., Andrianov I. MayAnd at SemEval-2016 Task 5: Syntactic and word2vec-based approach to aspect-based polarity detection in Russian. Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). – 2016. – pp. 325-329.Hercig T., Brychcin T., Svoboda L., Konkol M., Steinberger J. Unsupervised methods to improve aspect-based sentiment analysis in Czech. Computacion y Sistemas. – 2016. – vol. 20 (3), pp. 365-375. doi:10.13053/cys-20-3-2469Hercig T., Brychcin T., Svoboda L., Konkol M., Steinberger J. Unsupervised methods to improve aspect-based sentiment analysis in Czech. Computacion y Sistemas. – 2016. – vol. 20 (3), pp. 365-375. doi:10.13053/cys-20-3-2469Hercig T., Brychcin T., Svoboda L., Konkol M. Uwb at semeval-2016 task 5: Aspect based sentiment analysis. SemEval-2016. – 2016. – pp. 342-349.Hercig T., Brychcin T., Svoboda L., Konkol M. Uwb at semeval-2016 task 5: Aspect based sentiment analysis. SemEval-2016. – 2016. – pp. 342-349.

The authors declare that there are no conflicts of interest present.