Journal "Software Engineering"
a journal on theoretical and applied science and technology
ISSN 2220-3397

Issue N4 2026 year

DOI: 10.17587/prin.17.179-190
Methods for Extracting Emotional Assessment from Natural Language Texts based on Semantic Technologies and Deep Learning
D. E. Palchunov, D. Sc. (Phys. & Math.), Academician of RIA, Leading Researcher, palch@math.nsc.ru, Sobolev Institute of Mathematics of the Siberian Branch of the Russian Academy of Sciences, Novosibirsk, 630090, Russian Federation, V. S. Mironov, Postgraduate Student, v.mironov1@g.nsu.ru, Novosibirsk State University, 630090, Russian Federation
Corresponding author: Dmitry E. Palchunov, D. Sc. (Phys. & Math.), Academician of RIA, Leading Researcher, Sobolev Institute of Mathematics of the Siberian Branch of the Russian Academy of Sciences, Novosibirsk, 630090, Russian Federation, E-mail: palch@math.nsc.ru
Received on October 21, 2025
Accepted on November 21, 2025

Growing volume of text information in natural language these days makes it necessary to develop some valid emotional content analysis these days. The article suggests some methods of emotion recognition in the situations introduced in the Russian texts samples. Methods of identification and representation of emotion occurrence through atomic diagrams of partial models are also given in the article. Some program units for the LogicText software system are created to reveal and analyse the emotional evaluation. And to formalise emotionally colored situations we use evaluating partial models. Neural networks are used to recognise emotions. Causal relationships algorithm is based on dividing sentences into predicates and situations with the help of LogicText softwear system.

Keywords: sentiment analysis, emotion recognition, natural language processing, deep learning, ontological model, partial model, atomic diagram
pp. 179—190
For citation:
Palchunov D. E., Mironov V. S. Methods for Extracting Emotional Assessment from Natural Language Texts based on Semantic Technologies and Deep Learning, Programmnaya Ingeneria, 2026, vol. 17, no. 4, pp. 179—190. DOI: 10.17587/prin.17.179-190. (in Russian).
This work was carried out within the state assignment of the Sobolev Institute of Mathematics SB RAS (project FWNF-2022-0011).
References:
  1. Nandwani P., Verma R. A review on sentiment analysis and emotion detection from text, Social Network Analysis and Mining, 2021, vol. 11, no. 1, article 81. DOI: 10.1007/s13278-021-00776-6.
  2. Peng S., Cao L., Zhou Y. et al. A survey on deep learning for textual emotion analysis in social networks, Digital Communications and Networks, 2022, vol. 8, no. 5, pp. 745 —762. DOI: 10.1016/j.dcan.2021.10.003.
  3. Gennaro G., Ash E. Emotion and Reason in Political Language, The Economic Journal, 2022, vol. 132, no. 643, pp. 1037— 1059. DOI: 10.1093/ej/ueab104.
  4. Wang M., Hu F. The Application of NLTK Library for Python Natural Language Processing in Corpus Research, Theory and Practice in Language Studies, 2021, vol. 11, no. 9, pp. 1041—1049. DOI: 10.17507/tpls.1109.09.
  5. Ivan S. C., Gyorodi R. §., Gyorodi C. A. Sentiment Analysis Using Amazon Web Services and Microsoft Azure, Big Data and Cognitive Computing, 2024, vol. 8, no. 12, article 166. DOI: 10.3390/bdcc8120166.
  6. Abu-Salih B., Alhabashneh M., Zhu D. et al. Emotion detection of social data: APIs comparative study, Heliyon, 2023, vol. 9, no. 5, article e15926. DOI: 10.1016/j.heliyon.2023.e15926.
  7. Loukachevitch N. Automatic Sentiment Analysis of Texts: The Case of Russian, The Palgrave Handbook of Digital Russia Studies, Cham, Palgrave Macmillan, 2020, pp. 501—516. DOI: 10.1007/978-3-030-42855-6_28.
  8. Hua Y. C., Denny P., Wicker J., Taskova K. A system­atic review of aspect-based sentiment analysis: domains, methods, and trends, Artificial Intelligence Review, 2024, vol. 57, article 296. DOI: 10.1007/s10462-024-10906-z.
  9. Makhasoeva O. G., Palchunov D. E. Automated methods for constructing an atomic diagram of a model from natural language text, Vestnik of Novosibirsk State University. Series: Information Technologies, 2014, vol. 12, no. 2, pp. 64—73 (in Russian).
  10. Palchunov D. Application of FCA for Domain Model Theory Investigation, Artificial Intelligence. RCAI 2021. Lecture Notes in Artificial Intelligence, vol. 12948 / Eds. S. Kovalev, S. Kuznetsov, A. Panov, Springer International Publishing Ag, 2021, pp. 119—134. DOI: 10.1007/978-3-030-86855-0_9.
  11. Palchunov D. E., Akhmedov E. Yu. Development of logical methods for extracting emotional assessments from natural language texts, Proceedings of the 2023 IEEE 16th International Scientific and Technical Conference "Actual Problems of Electronic Instrument Engineering", APEIE, 2023, pp. 1460—1465.
  12. Palchunov D. E. Modeling Reasoning and Argumentation for the Development of Intelligent Assistants, 2022 IEEE Interna­tional Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON), Yekaterinburg, Russian Federation, 2022, pp. 820—825. DOI: 10.1109/SIBIRCON56155.2022.10017050.
  13. Pereira P., Moniz H., Carvalho J. P. Deep emotion recogni­tion in textual conversations: a survey, Artificial Intelligence Review, 2025, vol. 58, article 10. DOI: 10.1007/s10462-024-11010-y.
  14. Cowen A. S., Keltner D., Schroff F. et al. Sixteen facial expressions occur in similar contexts worldwide, Nature, 2021, vol. 589, no. 7841, pp. 251—257. DOI: 10.1038/s41586-020-3037-7.
  15. Chicho B. T., Sallow A. B. A Comprehensive Survey of Deep Learning Models Based on Keras Framework, Journal of Soft Computing and Data Mining, 2021, vol. 2, no. 2, pp. 49—62. DOI: 10.30880/jscdm.2021.02.02.005.
  16. Mienye I. D., Swart T. G., Obaido G. Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications, Information, 2024, vol. 15, no. 9, article 517. DOI: 10.3390/info15090517.
  17. Tian Y., Zhang Y. A comprehensive review on regularization strategies in machine learning, Information Fusion, 2022, vol. 77, pp. 146—166. DOI: 10.1016/j.inffus.2021.11.005.
  18. Abdulkadirov R. Survey of Optimization Algorithms in Modern Neural Networks, Mathematics, 2023, vol. 11, no. 11, article 2466. DOI: 10.3390/math11112466.
  19. Subramanian S., Ganapathiraman V., Barrett C. Hop, skip, jump to Convergence: Dynamics of Learning Rate Transitions for Improved Training of Large Language Models, Findings of the Association for Computational Linguistics: EMNLP 2024, 2024, pp. 16349—16362. DOI: 10.18653/v1/2024.findings-emnlp.954.
  20. Miseta T., Fodor A., Vathy-Fogarassy A. et al. Surpassing early stopping: A novel correlation-based stopping criterion for deep learning, Neurocomputing, 2024, vol. 578, article 127028. DOI: 10.1016/j.neucom.2023.127028.
  21. Raschka S. Machine Learning in Python: Main Developments and Technology Trends, Information, 2020, vol. 11, no. 4, article 193. DOI: 10.3390/info11040193.
  22. Demszky D., Movshovitz-Attias D., Ko J. et al. GoEmotions: A Dataset of Fine-Grained Emotions, Proc. of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020). Online, 5—10 July 2020, pp. 4040—4054. DOI: 10.18653/v1/2020. acl-main.372.
  23. Opitz J. A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice, Transactions of the Association for Computational Linguistics, 2024, vol. 12, pp. 820—836. DOI: 10.1162/tacl_a_00675.
  24. Nenasheva E. O., Palchunov D. E. Development of automated methods for transforming natural language sentences into quantifier-free predicate logic formulas, Vestnik NSU. Series: Information Technologies, 2017, vol. 15, no. 3, pp. 49—63. DOI: 10.25205/1818­7900-2017-15-3-49-63 (in Russian).
  25. Wegge M., Troiano E., Oberlander L. A. M., Klinger R. Experiencer-Specific Emotion and Appraisal Prediction, Proc. of the Fifth Workshop on NLP + CSS at EMNLP 2022, Abu Dhabi, ACL, 2022, pp. 25—32. DOI: 10.18653/v1/2022.nlpcss-1.3.
  26. Wang F., Ma H., Yu J. et al. SemEval-2024 Task 3: Multimodal Emotion Cause Analysis in Conversations, Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), 2024, pp. 2039—2050. DOI: 10.18653/v1/2024.semeval-1.277.