<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">kaz44</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник Университета Шакарима. Серия технические науки</journal-title><trans-title-group xml:lang="en"><trans-title>Bulletin of Shakarim University. Technical Sciences</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2788-7995</issn><issn pub-type="epub">3006-0524</issn><publisher><publisher-name>«Шәкәрім университеті» КеАҚ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.53360/2788-7995-2025-4(20)-3</article-id><article-id custom-type="elpub" pub-id-type="custom">kaz44-1953</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>АВТОМАТИЗАЦИЯ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ (ОРИГИНАЛЬНАЯ СТАТЬЯ)</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>AUTOMATION AND INFORMATION TECHNOLOGY (ORIGINAL ARTICLE)</subject></subj-group></article-categories><title-group><article-title>НЕЙРОСЕТЕВЫЕ МЕТОДЫ АНАЛИЗА ТЕКСТОВЫХ ОТЗЫВОВ ОБУЧАЮЩИХСЯ: АРХИТЕКТУРА, ОБУЧЕНИЕ И ИНТЕРПРЕТАЦИЯ РЕЗУЛЬТАТОВ</article-title><trans-title-group xml:lang="en"><trans-title>NEURAL NETWORK METHODS FOR ANALYZING TEXT FEEDBACK FROM STUDENTS: ARCHITECTURE, LEARNING, AND INTERPRETATION OF RESULTS</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-8681-4552</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Салыкова</surname><given-names>О. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Saltykova</surname><given-names>O. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ольга Сергеевна Cалыкова – кандидат технических наук, ассоциированный профессор кафедры «Программного обеспечения» </p><p>110000, Республика Казахстан, г. Костанай, ул. А. Байтурсынова, 47 </p></bio><bio xml:lang="en"><p>Olga Salykova – сandidate of technical sciences, associate professor of the Department of Software Engineering</p><p>110000, Republic of Kazakhstan, Kostanay, 47 A. Baitursynova street </p></bio><email xlink:type="simple">solga0603@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0001-2233-092X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Артыкбаева</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Artykbayeva</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Асель Айдарбековна Артыкбаева – докторант кафедры «Программного обеспечения»</p><p>110000, Республика Казахстан, г. Костанай, ул. А. Байтурсынова, 47</p></bio><bio xml:lang="en"><p>Assel Artykbayeva – doctoral student of the department of Software Engineering</p><p>110000, Republic of Kazakhstan, Kostanay, 47 A. Baitursynova street </p></bio><email xlink:type="simple">asel_aidarbekowna@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0000-4288-9774</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Искакова</surname><given-names>А. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Iskakova</surname><given-names>A. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Альмира Мухтаровна Искакова – докторант кафедры «Программного обеспечения»</p><p>110000, Республика Казахстан, г. Костанай, ул. А. Байтурсынова, 47 </p></bio><bio xml:lang="en"><p>Almira Iskakova – doctoral student of the department of Software Engineering</p><p>110000, Republic of Kazakhstan, Kostanay, 47 A. Baitursynova street</p></bio><email xlink:type="simple">n.a.almira.24@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0002-4459-5010</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Нурмагамбетова</surname><given-names>Л. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Nurmagambetova</surname><given-names>L. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ляйля Искендировна Нурмагамбетова – кандидат экономических наук, ассоциированный профессор ассоциированный профессор кафедры «Социально-экономических дисциплин»</p><p>110000, Республика Казахстан, г. Костанай, ул. Чернышевского, 59 </p></bio><bio xml:lang="en"><p>Lyailya Nurmagambetova – сandidate of еconomic sciences, associate professor, associate professor of the Department of Socio-economic disciplines</p><p>110000, Republic of Kazakhstan, Kostanay, 59 Chernyshevsky street </p></bio><email xlink:type="simple">Leila0205@mail.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru">Костанайский региональный университет имени Ахмет Байтұрсынұлы<country>Казахстан</country></aff><aff xml:lang="en">Kostanay Regional University named after Akhmet Baitursynuly<country>Kazakhstan</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru">Костанайский инженерно-экономический университет имени Мыржакыпа Дулатова<country>Казахстан</country></aff><aff xml:lang="en">Kostanay Engineering and Economics University named after Myrzhakyp Dulatov<country>Kazakhstan</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>25</day><month>01</month><year>2026</year></pub-date><volume>1</volume><issue>4(20)</issue><fpage>24</fpage><lpage>31</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Салыкова О.С., Артыкбаева А.А., Искакова А.М., Нурмагамбетова Л.И., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Салыкова О.С., Артыкбаева А.А., Искакова А.М., Нурмагамбетова Л.И.</copyright-holder><copyright-holder xml:lang="en">Saltykova O.S., Artykbayeva A.A., Iskakova A.M., Nurmagambetova L.I.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://tech.vestnik.shakarim.kz/jour/article/view/1953">https://tech.vestnik.shakarim.kz/jour/article/view/1953</self-uri><abstract><p>В статье представлен сравнительный анализ нейросетевых архитектур LSTM, BiLSTM и RuBERT, применяемых для автоматической классификации студенческих отзывов. Особое внимание уделено задачам предобработки данных, ручной разметки с учётом эмоциональной окраски и тематических аспектов, а также оценке надёжности корпуса с использованием коэффициента согласия Cohen’s kappa (0,82). Экспериментальные результаты показали, что RuBERT обеспечивает наивысшие значения Accuracy (0,87) и F1-score (0,85), что статистически подтверждено результатами t-теста. В то же время BiLSTM продемонстрировала более высокую эффективность по сравнению с LSTM благодаря учёту контекста в обеих направлениях. Проведённый анализ ошибок показал, что рекуррентные модели чаще всего путают нейтральные и отрицательные отзывы, а трансформерная архитектура лучше справляется с обработкой двусмысленных формулировок и скрытых эмоциональных оттенков. Практическая значимость исследования заключается в возможности интеграции разработанного подхода в системы LMS и цифровые образовательные платформы для автоматизации анализа обратной связи студентов. В качестве перспективных направлений обозначены расширение корпуса за счёт казахоязычных текстов и использование современных моделей семейства Transformer (RoBERTa, DeBERTa, ChatGLM).</p></abstract><trans-abstract xml:lang="en"><p>This article presents a comparative analysis of neural network architectures LSTM, BiLSTM, and RuBERT applied to the automatic classification of student feedback. Particular attention is paid to data preprocessing, manual annotation with consideration of sentiment and thematic aspects, as well as corpus reliability assessment using Cohen’s kappa coefficient (0.82). The experimental results show that RuBERT achieves the highest Accuracy (0.87) and F1-score (0.85), which is statistically confirmed by t-test results. At the same time, BiLSTM demonstrates higher efficiency compared to LSTM due to its ability to capture bidirectional context. Error analysis revealed that recurrent models most often confuse neutral and negative feedback, while the transformer-based architecture performs better in handling ambiguous expressions and subtle emotional nuances. The practical significance of the study lies in the possibility of integrating the proposed approach into LMS and digital educational platforms to automate the analysis of student feedback. Future research directions include expanding the corpus with Kazakh-language texts and applying advanced Transformer-based models (RoBERTa, DeBERTa, ChatGLM).</p></trans-abstract><kwd-group xml:lang="ru"><kwd>нейросетевой анализ текста</kwd><kwd>образовательная аналитика</kwd><kwd>BERT</kwd><kwd>LSTM</kwd><kwd>автоматическая классификация</kwd><kwd>обработка текстов</kwd><kwd>обратная связь студентов</kwd><kwd>интеллектуальные системы образования</kwd></kwd-group><kwd-group xml:lang="en"><kwd>neural network text analysis</kwd><kwd>educational analytics</kwd><kwd>BERT</kwd><kwd>LSTM</kwd><kwd>automatic classification</kwd><kwd>text preprocessing</kwd><kwd>student feedback</kwd><kwd>intelligent educational systems</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Васнецова Е.Л. Применение методов анализа тональности в образовательной среде / Е.Л. Васнецова, Д.А. Семенов // Образовательные технологии и общество. – 2021. – № 24(1). – С.105-116.</mixed-citation><mixed-citation xml:lang="en">Vasnetsova E.L. Primenenie metodov analiza tonal'nosti v obrazovatel'noi srede / E.L. Vasnetsova, D.A. Semenov // Obrazovatel'nye tekhnologii i obshchestvo. – 2021. – № 24(1). – S.105-116. (In Russian).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Efficient estimation of word representations in vector space / Т. Mikolov et al // arXiv preprint arXiv:1301.3781, 2013.</mixed-citation><mixed-citation xml:lang="en">Efficient estimation of word representations in vector space / T. Mikolov et al // arXiv preprint arXiv:1301.3781, 2013. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Cortes C. Support-vector networks / C. Cortes, V. Vapnik // Machine Learning. – 1995. – № 20(3). – Р. 273-297.</mixed-citation><mixed-citation xml:lang="en">Cortes C. Support-vector networks / C. Cortes, V. Vapnik // Machine Learning. – 1995. – № 20(3). – R. 273-297. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Schuster M.K. Bidirectional recurrent neural networks / M. Schuster, K.K. Paliwal // IEEE Transactions on Signal Processing. – 1997. – № 45(11). – Р. 2673-2681.</mixed-citation><mixed-citation xml:lang="en">Schuster M.K. Bidirectional recurrent neural networks / M. Schuster, K.K. Paliwal // IEEE Transactions on Signal Processing. – 1997. – № 45(11). – R. 2673-2681. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Hochreiter S. Long short-term memory / S. Hochreiter, J. Schmidhuber // Neural Computation. – 1997. – № 9(8). – Р. 1735-1780.</mixed-citation><mixed-citation xml:lang="en">Hochreiter S. Long short-term memory / S. Hochreiter, J. Schmidhuber // Neural Computation. – 1997. – № 9(8). – R. 1735-1780. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">RoBERTa – BiLSTM: A Context – Aware Hybri Model for Sentiment Analysis / Rahman M.M. et al // arXiv preprint arXiv:2406.00367. – 2024. https://doi.org/10.48550/arXiv.2406.00367.</mixed-citation><mixed-citation xml:lang="en">RoBERTa – BiLSTM: A Context – Aware Hybri Model for Sentiment Analysis / Rahman M.M. et al // arXiv preprint arXiv:2406.00367. – 2024. https://doi.org/10.48550/arXiv.2406.00367. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">BERT: Pre-training of deep bidirectional transformers for language understanding / J. Devlin et al // Proceedings of NAACL-HLT. – 2019. – Р. 4171-4186.</mixed-citation><mixed-citation xml:lang="en">BERT: Pre-training of deep bidirectional transformers for language understanding / J. Devlin et al // Proceedings of NAACL-HLT. – 2019. – R. 4171-4186. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">RoBERTa: A robustly optimized BERT pretraining approach / Y. Liu et al // arXiv preprint arXiv:1907. – 2019. – Р. 11692.</mixed-citation><mixed-citation xml:lang="en">RoBERTa: A robustly optimized BERT pretraining approach / Y. Liu et al // arXiv preprint arXiv:1907. – 2019. – R. 11692. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Lin F. Sentiment analysis in online education: An analytical approach and application / F. Lin // Proceedings of the International Conference on Machine Learning and Automation. – 2024.</mixed-citation><mixed-citation xml:lang="en">Lin F. Sentiment analysis in online education: An analytical approach and application / F. Lin // Proceedings of the International Conference on Machine Learning and Automation. – 2024. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">An improved neural network model for sentiment analysis in online education / В. Xu et al // Journal of Intelligent &amp; Fuzzy Systems. – 2020. – № 38(3). – Р. 3651-3662.</mixed-citation><mixed-citation xml:lang="en">An improved neural network model for sentiment analysis in online education / V. Xu et al // Journal of Intelligent &amp; Fuzzy Systems. – 2020. – № 38(3). – R. 3651-3662. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Elevating educational insights: Sentiment analysis of faculty feedback using advanced machine learning models / S.B. Deshpande et al // Advances in Continuous and Discrete Models. – 2025.</mixed-citation><mixed-citation xml:lang="en">Elevating educational insights: Sentiment analysis of faculty feedback using advanced machine learning models / S.B. Deshpande et al // Advances in Continuous and Discrete Models. – 2025. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang W. Comparative evaluation of Transformer-based models for multilingual sentiment analysis / W. Zhang, L. Xu, J. Wang // Journal of Artificial Intelligence Research. – 2024. – № 71. – Р. 55-72.</mixed-citation><mixed-citation xml:lang="en">Zhang W. Comparative evaluation of Transformer-based models for multilingual sentiment analysis / W. Zhang, L. Xu, J. Wang // Journal of Artificial Intelligence Research. – 2024. – № 71. – R. 55-72. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Xu R. Advances in DeBERTa for educational text mining / R. Xu, H. Chen, Z. Huang // Computers &amp; Education. – 2025. – № 198. – Р. 104719.</mixed-citation><mixed-citation xml:lang="en">Xu R. Advances in DeBERTa for educational text mining / R. Xu, H. Chen, Z. Huang // Computers &amp; Education. – 2025. – № 198. – R. 104719. (In English).</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Li X. Sentiment analysis in educational contexts: Comparing LSTM and BiLSTM approaches / X. Li, Y. Zhang, H. Zhao // Education and Information Technologies. – 2023. – № 28(2). – Р. 213-229.</mixed-citation><mixed-citation xml:lang="en">Li X. Sentiment analysis in educational contexts: Comparing LSTM and BiLSTM approaches / X. Li, Y. Zhang, H. Zhao // Education and Information Technologies. – 2023. – № 28(2). – R. 213-229. (In English).</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
