Moscow, Moscow, Russian Federation
Russian Federation
UDC 81
This article focuses on determining the emotional sentiment of Russian-language texts using neural network models, particularly DeepSeek. In the context of digitalization, identifying markers that represent the tone of a statement (negative or positive) has become increasingly relevant for two main reasons: first, it saves researchers’ time, and second, it ensures impartiality by eliminating authorial interpretation. However, existing language models, primarily trained on English-language corpora, show limited accuracy when applied to Russian texts—especially in detecting positive sentiment. The challenge of identifying tonal markers is further complicated by the stylistic diversity of linguistic expressions conveying positive or negative emotionality in user discourse. Thus, testing DeepSeek’s performance in a Russian-language digital environment helps reveal typical distortions in its interpretation of evaluative context and outlines potential improvements for existing neural network models in analyzing Russian discourse.
sentiment analysis, text tonality, emotional coloring of text, neural network models, DeepSeek, RuSentiment
1. Sosnina Yu.A. Emotivnost' vnutrenney formy slova: po dannym metayazykovoy deyatel'nosti nositeley russkogo yazyka [Emotivity of the internal form of a word: based on the metalinguistic activity of native Russian speakers]. Kemerovo, 2009. 184 p. (in Russian) EDN: https://elibrary.ru/QEMYIP
2. Zhaksybaev D.O., Mizamova G.N. Algoritmy obrabotki estestvennogo yazyka dlya ponimaniya semantiki teksta [Natural language processing algorithms for understanding text semantics]. Trudy ISP RAN [Proceedings of the ISP RAS]. 2022, no. 1. URL: https://cyberleninka.ru/article/n/algoritmy-obrabotki-estestvennogo-yazyka-dlya-ponimaniya-semantiki-teksta (accessed: 25.04.2025) (in Russian) DOI: https://doi.org/10.15514/ISPRAS-2022-34(1)-10; EDN: https://elibrary.ru/ICYKEQ
3. Savenkov P.A., Voloshko A.G., Ivutin A.N., Kryukov O.S. Formirovanie vektora povedencheskikh priznakov na osnove LSTM i GRU setey [Formation of a behavioral feature vector based on LSTM and GRU networks]. Izvestiya TulGU. Tekhnicheskie nauki [News of Tula State University. Technical Sciences]. 2024, no. 12. URL: https://cyberleninka.ru/article/n/formirovanie-vektora-povedencheskih-priznakov-na-osnove-lstm-i-gru-setey (accessed: 18.04.2025) (in Russian) DOI: https://doi.org/10.24412/2071-6168-2024-12-213-214; EDN: https://elibrary.ru/OADBYE
4. Bogdanov A.L., Dulya I.S. Sentiment-analiz korotkikh russkoyazychnykh tekstov v sotsial'nykh media [Sentiment analysis of short Russian-language texts in social media]. Vestnik Tomskogo gosudarstvennogo universiteta. Ekonomika [Bulletin of Tomsk State University. Economics]. 2019, no. 47. URL: https://cyberleninka.ru/article/n/sentiment-analiz-korotkih-russkoyazychnyh-tekstov-v-sotsialnyh-media (accessed: 23.04.2025) (in Russian) DOI: https://doi.org/10.17223/19988648/47/17; EDN: https://elibrary.ru/QFXMQA
5. Imber S.Yu., Tomskaya M.V. Vozmozhnost' primeneniya neyroseti GPT-4 v lingvisticheskom issledovanii: na primere analiza emotivnykh tekstov [The possibility of using GPT-4 neural network in linguistic research: on the example of emotive text analysis]. Sotsial'nye i gumanitarnye nauki. Otechestvennaya i zarubezhnaya literatura. Seriya 6. Yazykoznanie [Social and Human Sciences. Domestic and Foreign Literature. Series 6. Linguistics]. 2024, no. 4, pp. 126–138. DOI:https://doi.org/10.31249/ling/2024.04.07 (in Russian) EDN: https://elibrary.ru/BYKOBA
6. Gukosyants O.Yu., Alimuradov O.A. Eksplitsitnye i implitsitnye markery konfliktnogo rechevogo povedeniya v internet-oposredovannoy kommunikatsii perioda pandemii COVID-19 [Explicit and implicit markers of conflict speech behavior in Internet-mediated communication during the COVID-19 pandemic]. Nauchnye issledovaniya i razrabotki. Sovremennaya kommunikativistika [Scientific Research and Development. Modern Communication Studies]. 2023, no. 6, pp. 94–104. DOI:https://doi.org/10.12737/2587-9103-2023-12-6-94-104 (accessed: 18.04.2025) (in Russian) EDN: https://elibrary.ru/VUUDCG
7. Gukasyan Ts.G. Vektornye modeli na osnove simvol'nykh n-gramm dlya morfologicheskogo analiza tekstov [Vector models based on character n-grams for morphological text analysis]. Trudy ISP RAN [Proceedings of the ISP RAS]. 2020, no. 2. URL: https://cyberleninka.ru/article/n/vektornye-modeli-na-osnove-simvolnyh-n-gramm-dlya-morfologicheskogo-analiza-tekstov (accessed: 16.04.2025) (in Russian) DOI: https://doi.org/10.15514/ISPRAS-2020-32(2)-1; EDN: https://elibrary.ru/LVVKJC
8. Maulud D., Zeebaree S., Jacksi K., Sadeeq M., Hussein K. State of Art for Semantic Analysis of Natural Language Processing. Qubahan Academic Journal. 2021, vol. 1, no. 2, pp. 21–28. DOI:https://doi.org/10.48161/qaj.v1n2a40.
9. Greff K., Srivastava R.K., Koutník J., Steunebrink B.R., Schmidhuber J. LSTM: A Search Space Odyssey. IEEE Transactions on Neural Networks and Learning Systems. 2017. URL: https://arxiv.org/pdf/1503.04069.pdf. DOI: https://doi.org/10.1109/TNNLS.2016.2582924
10. Cliche M. BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs. *Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)*. 2017, pp. 573–580. DOI:https://doi.org/10.18653/v1/S17-2094.
11. Khan T., Durrani M., Ali A., Inayat I., Khalid S., Khan K. Sentiment analysis and the complex natural language. Complex Adaptive Systems Modeling. 2016, vol. 4. DOI:https://doi.org/10.1186/s40294-016-0016-9.
12. Luo T., Chen S., Xu G., Zhou J. Sentiment Analysis. In: Social Media Retrieval. London, Springer, 2013. DOI:https://doi.org/10.1007/978-1-4614-7202-5_4.
13. Smetanin S. The Applications of Sentiment Analysis for Russian Language Texts: Current Challenges and Future Perspectives. IEEE Access. 2020. DOI:https://doi.org/10.1109/ACCESS.2020.3002215.
14. Semina T.A. Analiz tonal'nosti teksta: sovremennye podkhody i sushchestvuyushchie problemy [Sentiment analysis of text: modern approaches and existing problems]. Sotsial'nye i gumanitarnye nauki. Otechestvennaya i zarubezhnaya literatura. Ser. 6, Yazykoznanie [Social and Human Sciences. Domestic and Foreign Literature. Ser. 6, Linguistics]. 2020, no. 4. URL: https://cyberleninka.ru/article/n/analiz-tonalnosti-teksta-sovremennye-podhody-i-suschestvuyuschie-problemy (accessed: 23.04.2025) (in Russian) EDN: https://elibrary.ru/ICGXZF
15. Chen Y., Yuan J., You Q., Luo J. Twitter Sentiment Analysis via Bi-sense Emoji Embedding and Attention-based LSTM. Proceedings of the 26th ACM
