Sentiment Analysis as a Tool of Linguistic Emotionology: Assessment of the Text Tonality Analysis Systems Potential
- Autores: Maksimenko O.I.1, Belyakov M.V.2
-
Afiliações:
- Federal State university of education
- Moscow State institute of international Relations (university) Ministry of Foreign affairs of the Russian Federation
- Edição: Volume 16, Nº 3 (2025): Phraseology. Paremiology. Culture: on the anniversary of V.M. Mokienko
- Páginas: 760-782
- Seção: FUNCTIONAL SEMANTICS
- URL: https://journal-vniispk.ru/2313-2299/article/view/354192
- DOI: https://doi.org/10.22363/2313-2299-2025-16-3-760-782
- EDN: https://elibrary.ru/DCBVEJ
- ID: 354192
Citar
Texto integral
Resumo
The assessment of text tone in large information flows is solved using both qualitative and quantitative methods. Qualitative methods include, primarily, the methods of linguistic emotionology, such as the compilation of tone dictionaries used in computer systems to evaluate the tone of a given text. the article discusses the principles of functioning of automatic text analysis systems as a method of computer-aided text analysis. it also provides an analysis of several modern tone analysis systems. characteristics of these systems are identified, and advantages and disadvantages are revealed based on linguistic material from marked-up film and product reviews from a well-known online marketplace. Special attention is given to linguistic reasons behind the challenges in assessing tone, such as multilingualism, different ways of presenting text by users, including abbreviated forms, can make the process difficult to understand. Genre diversity, implicit assessments, polysemy, homonymy, polarity modifiers, subjunctive mood, sarcasm, irony are all factors that can complicate the process of determining the tonality of a piece of text. Based on the results of our study, we conclude that programs using a hybrid method have the most effective functionality for detecting tonality. these programs are an important tool for linguistic emotionology and linguoconflictology, as they provide a necessary evaluative component. the research suggests possible approaches for optimizing the functioning of these programs. the study allows us to gain a better understanding of the challenges associated with detecting tonality in text and selecting sentiment analysis systems that operate on different principles. these systems not only solve practical problems related to sentiment analysis but also serve as a valuable source of material for research within the linguistic theory of emotions.
Palavras-chave
Sobre autores
Olga Maksimenko
Federal State university of education
Autor responsável pela correspondência
Email: maxbel7@yandex.ru
ORCID ID: 0000-0002-6611-8744
Código SPIN: 7708-5901
Dr.Sc. (Philology), Full Professor, Professor of the language theory, anglistics and applied linguistics Department, linguistic Faculty
10a built 2, Radio street, Moscow, Russian Federation, 105005Mikhail Belyakov
Moscow State institute of international Relations (university) Ministry of Foreign affairs of the Russian Federation
Email: m.belyakov@my.mgimo.ru
ORCID ID: 0000-0002-6230-9893
Código SPIN: 1761-5400
Dr.Sc. (Philology), associated Professor, Professor at Russian Department
76, Vernadskogo av., Moscow, Russian Federation, 119454Bibliografia
- Shakhovsky, V.I. (1987). Categorization of Emotions in the Lexico-Semantic System of Language. Voronezh: Voronezh State University publ. (In Russ.).
- Shakhovsky, V.I. (2008). Linguistic Theory of Emotions. Moscow: Gnosis. (In Russ.).
- Belyakov, M.V. (2022). Linguoaxiology and Linguosemiotics of Diplomatic discourse (based on the Material of Open Professional Diplomacy) [Doctoral Thesis]. Moscow. (In Russ.).
- Belyakov, M.V. (2016). Analysis of News Reports on the Website of the Ministry of Foreign Affairs of the Russian Federation by the Method of Sentiment Analysis (Art. 2). RUDN Journal of Language Studies, Semiotics and Semantics, 6(4), 115–124. (In Russ.).EDN: WZZKRZ
- Maksimenko, O.I. (2012). Analysis of the Tonality of Texts (Sentiment Analysis) Based on Media Texts. In: Proceedings of IV Novikov readings: Functional Semantics and Semiotics of Sign Systems. Part 1 (pp. 96–105). Moscow: RUDN University publ. (In Russ.).
- Introduction to Sentiment Analysis: What is Sentiment Analysis (2018). URL: https://algorithmia.com/blog/introduction-sentiment-analysis (accessed: 10.01.2025).
- Agrawal, R., & Gupta, N. (2018). Extracting Knowledge from Opinion Mining. In: Advances in Data Mining and Database Management. Hershey: IGI Global. https://doi.org/ 10.4018/978-1-5225-6117-0
- Yurganov, A.A. (2017). Sentiment Analysis as a Tool for Text Research. Problems of Modern Science and Education, 29(111), 39–41. (In Russ.). EDN: ZDMSVF
- Pang, B., & Lee, L. (2008). Opining Mining and Sentiment Analysis. Foundations and Trends in Information Retrieval, 2(1–2), 1–135.
- Shakhovsky, V.I. (2009). Emotions as an Object of Research in Linguistics. Journal of Psycholinguistics, 9, 29–43. (In Russ.). EDN: LAULHF
- Kolmogorova, A.V., Kalinin, A.A., & Malikova, A.V. (2019). Who Speaks about What in “Joyful” and “Sad” Texts: in Search of Discriminating Features of Texts of Different Emotional Tones. Proceedings of the Ural Federal University. Series 2, Humanities, 21(4(193)), 219—234. (In Russ.). https://doi.org/ 10.15826/izv2.2019.21.4.078 EDN: JMPVSS
- Kolmogorova, A.V., & Vdovina, L.A. (2019). Lexico-Grammatical Markers of Emotions as Parameters for The Sentimental Analysis of Russian-Language Internet Texts. Bulletin of the Perm University. Russian and Foreign Philology, 11(3), 38–46. (In Russ.). https://doi.org/ 10.17072/2073-6681-2019-3-38-46 EDN: VOGAAV
- Kolmogorova, A.V. (2018). Verbal Markers of Emotions in the Context of Solving Problems of Sentiment Analysis. Questions of Cognitive Linguistics, Issues of Cognitive Linguistics, 1(54), 83—93. (In Russ.). https://doi.org/ 10.20916/1812-3228-2018-1-83-93 EDN: QIWKPN
- Semina, T.A. (2018). Dichotomy Subjectivity vs. Objectivity and Tonal Relevance in the Tasks of Tonality Analysis. Bulletin of the Moscow State Regional University. Series: Linguistics, 1, 38–45. (In Russ.). https://doi.org/ 10.18384/2310-712X-2018-1-38-45 EDN: YRNQNH
- Scheible, C., & Schutze, H. (2013). Sentiment Relevance. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, August 4–9. (pp. 954–963). Sofia, Bulgaria: Association for Computational Linguistics.
- Narayanan, R., Liu, B., & Choudhary, A. (2009). Sentiment Analysis of Conditional Sentences. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (pp. 180–189). Singapore: ACL and AFNLP. URL: https://www.researchgate.net/publication/221012837_Sentiment_Analysis_of_Conditional_Sentences (accessed: 10.01.2025). https://doi.org/ 10.3115/1699510.1699534
- Failures, A.G., Voronina, I.E., et al. (2016). Advanced Neural Network Models for Solving the Problem of Determining Tonality. Proceedings of Voronezh State University. Series: Systems Analysis and Information Technologies, 4, 178–183. EDN: XVSYZX
- Rentoumi, V., Petrakis, S., Klenner, M. et al. (2010). United We Stand: Improving Sentiment Analysis by Joining Machine Learning and Rule Based Methods. In: 7th International Conference on Language Resources and Evaluation (LREC 2010), 19–21 May 2010 (pp. 954–963). Malta: Zurich Open Repository and Archive, University of Zurich.
- Becker, I., & Aharonson, V. (2010). Last but definitely not least: on the role of the last sentence in automatic polarity-classification. In: Proceedings of the ACL 2010 Conference Short Papers 11–16 July 2010 (pp. 331–335). Sweden: Uppsala, Association for Computational Linguistics URL: https://www.researchgate.net/publication/220873476_Last_but_Definitely_Not_Least_On_the_Role_of_the_Last_Sentence_in_Automatic_Polarity-Classification (accessed: 10.01.2025).
- Shakhovsky, V.I. (2019). Substantiation of the Linguistic Theory of Emotions. Journal of psycholinguistics, 1(39), 22–37. (In Russ.). https://doi.org/ 10.30982/2077-5911-2019-39-1-22-37 EDN: SKQDYO
Arquivos suplementares

