<?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">sibsutis</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник СибГУТИ</journal-title><trans-title-group xml:lang="en"><trans-title>The Herald of the Siberian State University of Telecommunications and Information Science</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1998-6920</issn><publisher><publisher-name>СибГУТИ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.55648/1998-6920-2025-19-4-3-16</article-id><article-id custom-type="elpub" pub-id-type="custom">sibsutis-997</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>Статьи</subject></subj-group></article-categories><title-group><article-title>Анализ тональности узбекских текстов с использованием NER: сравнительное исследование моделей SVM, LSTM и BERT</article-title><trans-title-group xml:lang="en"><trans-title>Sentiment analysis of Uzbek texts using NER: a comparative study of SVM, LSTM, and BERT models</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0000-5540-2013</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Саидов</surname><given-names>Бобур Рашидович</given-names></name><name name-style="western" xml:lang="en"><surname>Saidov</surname><given-names>Bobur Rashidovich</given-names></name></name-alternatives><bio xml:lang="ru"><p>аспирант, Новосибирский государственный университет</p></bio><bio xml:lang="en"><p>PhD student of Department of Mathematical modeling, numerical methods and software packages</p></bio><email xlink:type="simple">b.saidov@g.nsu.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/0000-0003-3299-0507</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Барахнин</surname><given-names>Владимир Борисович</given-names></name><name name-style="western" xml:lang="en"><surname>Barakhnin</surname><given-names>Vladimir Borisovich</given-names></name></name-alternatives><bio xml:lang="ru"><p>доктор технических наук, доцент, Новосибирский государственный университет</p></bio><bio xml:lang="en"><p>Doctor of Technical Sciences, Associate Professor, Novosibirsk State University Novosibirsk, Russia. Federal Research Center for Information and Computational Technologies Novosibirsk, Russia</p></bio><email xlink:type="simple">v.barakhnin@g.nsu.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Новосибирский национальный исследовательский государственный университет</institution><country>Узбекистан</country></aff><aff xml:lang="en"><institution>Novosibirsk State University</institution><country>Uzbekistan</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Новосибирский национальный исследовательский государственный университет; Федеральный исследовательский центр информационных и вычислительных технологий</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Novosibirsk State University; Federal Research Center for Information and Computational Technologies</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>22</day><month>12</month><year>2025</year></pub-date><volume>19</volume><issue>4</issue><issue-title>Вестник СибГУТИ</issue-title><fpage>3</fpage><lpage>17</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Саидов Б.Р., Барахнин В.Б., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Саидов Б.Р., Барахнин В.Б.</copyright-holder><copyright-holder xml:lang="en">Saidov B.R., Barakhnin V.B.</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://vestnik.sibsutis.ru/jour/article/view/997">https://vestnik.sibsutis.ru/jour/article/view/997</self-uri><abstract><p>В данной статье проводится сравнительный анализ методов машинного обучения (SVM), глубокого обучения (LSTM) и трансформерных моделей (BERT) для классификации тональности узбекских текстов с использованием распознавания именованных сущностей (NER). Исследование направлено на решение проблемы точного определения эмоциональной окраски в морфологически сложных языках с ограниченными ресурсами, на примере узбекского – тюркского языка с агглютинативной структурой. Для экспериментов использован датасет из 10 000 пользовательских комментариев из социальных сетей, аннотированных вручную (тональность: положительная, отрицательная,нейтральная) и автоматически (NER через CRF-модель для идентификации брендов, локаций и публичных лиц). Интеграция NER позволила устранить контекстуальные неоднозначности, например, разграничение предложений: «Обожаю историю Самарканда» (положительный оттенок) и «Пробки в Самарканде невыносимы» (отрицательный). Результаты показали, что BERT, дообученный на узбекских текстах, достиг наивысшей точности (90.2%) благодаря контекстуализированным эмбеддингам, связывающим сущности с тональностью. LSTM продемонстрировал конкурентоспособную точность (85.1%) в анализе последовательностей, но требовал больших объёмов данных. SVM, несмотря на вычислительную эффективность, показал скромные результаты (78.3%) из-за неспособности учитывать лингвистические нюансы. Исследование подчеркивает важность NER для низкоресурсных языков в устранении неоднозначности и предлагает рекомендации по внедрению BERT в прикладные задачи (например, анализ отзывов). Обсуждаются ограничения, включая недостаток данных и высокие вычислительные затраты, что определяет направления будущих исследований для оптимизации моделей под узбекский язык.</p></abstract><trans-abstract xml:lang="en"><p>This paper presents a comparative analysis of machine learning (SVM), deep learning (LSTM), and transformer-based (BERT) models for sentiment classification in Uzbek texts, enhanced by Named Entity Recognition (NER). The study addresses the challenge of accurately detecting sentiment in morphologically complex languages with limited resources, focusing on Uzbek–a Turkic language with rich agglutinative structures. A dataset of 10,000 user-generated comments from social platforms was annotated using a hybrid approach: manual labeling for sentiment (positive, negative, neutral) and a CRF-based NER system to identify entities (e.g., brands, locations, public figures). The integration of NER features aimed to resolve contextual ambiguities, such as distinguishing between "I love Samarkand’s history" (positive) and "Samarkand’s traffic is unbearable" (negative). Experimental results demonstrate that BERT, fine-tuned on Uzbek text, achieved the highest accuracy (90.2%) by leveraging contextualized embeddings to align entities with sentiment. LSTM showed competitive performance (85.1%) in sequential pattern learning but required extensive training data. SVM, while computationally efficient, lagged at 78.3% accuracy due to its inability to capture nuanced linguistic dependencies. The findings emphasize the critical role of NER in low-resource languages for disambiguating sentiment triggers and propose practical guidelines for deploying BERT in real-world applications, such as customer feedback analysis. Limitations, including data scarcity and computational costs, are discussed to inform future research on optimizing lightweight models for Uzbek NLP tasks.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>анализ тональности</kwd><kwd>распознавание именованных сущностей (NER)</kwd><kwd>узбекский язык</kwd><kwd>BERT</kwd><kwd>низкоресурсная обработка естественного языка</kwd></kwd-group><kwd-group xml:lang="en"><kwd>Sentiment Analysis</kwd><kwd>Named Entity Recognition</kwd><kwd>Uzbek Language</kwd><kwd>BERT</kwd><kwd>Low-&#13;
Resource NLP</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Исследование выполнено в рамках государственного задания Министерства науки и высшего образования Российской Федерации для Федерального научно-исследовательского центра информационных и вычислительных технологий.</funding-statement><funding-statement xml:lang="en">The research was carried out within the state assignment of Ministry of Science and Higher Education of the Russian Federation for Federal Research Center for Information and Computational Technologies.</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Lample G., Ballesteros M., Subramanian S., Kawakami K., Dyer C. Neural Architectures for Named Entity Recognition. NAACL-HLT, 2016, p. 260–270. DOI: 10.18653/v1/N161030</mixed-citation><mixed-citation xml:lang="en">Lample G., Ballesteros M., Subramanian S., Kawakami K., Dyer C. Neural Architectures for Named Entity Recognition // Proceedings of NAACL-HLT. – 2016. – P. 260–270. DOI: 10.18653/v1/N16-1030</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Bojanowski P., Grave E., Joulin A., Mikolov T. Enriching Word Vectors with Subword Information. arXiv preprint arXiv:1607.04606, 2016, 12 p. URL: https://arxiv.org/abs/1607.04606</mixed-citation><mixed-citation xml:lang="en">Bojanowski P., Grave E., Joulin A., Mikolov T. Enriching Word Vectors with Subword Information // arXiv preprint arXiv:1607.04606. – 2016. – 12 p. URL: https://arxiv.org/abs/1607.04606</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Liu Y., Ott M., Goyal N., Du J., Joshi M. RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692, 2019, 13 p.</mixed-citation><mixed-citation xml:lang="en">Liu Y., Ott M., Goyal N., Du J., Joshi M. RoBERTa: A Robustly Optimized BERT Pretraining Approach // arXiv preprint arXiv:1907.11692. – 2019. – 13 p.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Xolmirzayev A., Yusupov S. Rule-Based Sentiment Analysis for Uzbek Texts, International Conference on Information Science and Communications Technologies (ICISCT), 2021, p. 1–4.</mixed-citation><mixed-citation xml:lang="en">Xolmirzayev A., Yusupov S. Rule-Based Sentiment Analysis for Uzbek Texts // Proceedings of the International Conference on Information Science and Communications Technologies (ICISCT). – 2021. – P. 1–4.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Hochreiter S., Schmidhuber J. Long Short-Term Memory. Neural Computation, 1997, Vol. 9(8), p. 1735–1780. DOI: 10.1162/neco.1997.9.8.1735</mixed-citation><mixed-citation xml:lang="en">Hochreiter S., Schmidhuber J. Long Short-Term Memory // Neural Computation. – 1997. – Vol. 9(8). – P. 1735–1780. DOI: 10.1162/neco.1997.9.8.1735</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Lample G., Ballesteros M., Subramanian S., Kawakami K., Dyer C. Neural Architectures for Named Entity Recognition. NAACL-HLT, 2016, p. 260–270.</mixed-citation><mixed-citation xml:lang="en">Lample G., Ballesteros M., Subramanian S., Kawakami K., Dyer C. Neural Architectures for Named Entity Recognition // Proceedings of NAACL-HLT. – 2016. – P. 260–270.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Kuriyozov Z., Muhamediev R. Uzbek Language Processing: Challenges and Opportunities. International Journal of Advanced Computer Science and Applications, 2020, vol. 11(6), p. 123–130. DOI: 10.14569/IJACSA.2020.0110616</mixed-citation><mixed-citation xml:lang="en">Kuriyozov Z., Muhamediev R. Uzbek Language Processing: Challenges and Opportunities // International Journal of Advanced Computer Science and Applications. – 2020. – Vol. 11(6). – P. 123–130. DOI: 10.14569/IJACSA.2020.0110616</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Zero-shot sentiment analysis: e.g., Yin et al. (2020)</mixed-citation><mixed-citation xml:lang="en">Tjong Kim Sang E., De Meulder F. Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition // Proceedings of CoNLL-2003. – 2003. – P. 142–147. URL: https://aclanthology.org/W03-0419</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Transfer learning for low-resource languages: e.g., Conneau et al. (2020)</mixed-citation><mixed-citation xml:lang="en">Hochreiter S., Schmidhuber J. Long Short-Term Memory // Neural Computation. – 1997. – Vol. 9(8). – P. 1735–1780.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Lightweight BERT models: Jiao et al. (2019), Sanh et al. (2019)</mixed-citation><mixed-citation xml:lang="en">Mikolov T., Chen K., Corrado G., Dean J. Efficient Estimation of Word Representations in Vector Space // arXiv preprint arXiv:1301.3781. – 2013. – 12 p. URL: https://arxiv.org/abs/1301.3781</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Devlin J., Chang M., Lee K., Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805, 2018, 16 p. URL: https://arxiv.org/abs/1810.04805</mixed-citation><mixed-citation xml:lang="en">Devlin J., Chang M., Lee K., Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding // arXiv preprint arXiv:1810.04805. – 2018. – 16 p. URL: https://arxiv.org/abs/1810.04805</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L. Attention Is All You Need. Advances in Neural Information Processing Systems (NIPS), 2017, p. 5998–6008. URL: https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html</mixed-citation><mixed-citation xml:lang="en">Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L. Attention Is All You Need // Advances in Neural Information Processing Systems (NIPS). – 2017. – P. 5998–6008. URL:</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Saidov B. R., Barakhnin V. B., Sharipov E. J., Maksetbaev A. B., Ruzimov J. O., Abdullayev R. M. Development and Realization of Software Application for Syntax Checking of Karakalpak Language Text. IEEE 3rd International Conference on Problems of Informatics, Electronics and Radio Engineering (PIERE), 2024. https://ieeexplore.ieee.org/document/10804984</mixed-citation><mixed-citation xml:lang="en">https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aaAbstract.html</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Yusupov F., Abdullaev S. Named Entity Recognition for Uzbek Using Conditional Random Fields. AINL-ISMW, 2019, p. 45–52. URL: https://ceur-ws.org/Vol-2499/paper11.pdf</mixed-citation><mixed-citation xml:lang="en">Pang B., Lee L. Opinion Mining and Sentiment Analysis // Foundations and Trends in Information Retrieval. – 2008. – Vol. 2. – P. 1–135.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Abidov A., Mirzaev T. UzBERT: A Pretrained Language Model for Uzbek. Technical Report, Tashkent University of Information Technologies, 2022, 25 p. URL: https://archive.org/details/uzbert-report</mixed-citation><mixed-citation xml:lang="en">Yusupov F., Abdullaev S. Named Entity Recognition for Uzbek Using Conditional Random Fields // Proceedings  of AINL-ISMW. – 2019. – P. 45–52. URL: https://ceurws.org/Vol-2499/paper11.pdf</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Sutton C., McCallum A. An Introduction to Conditional Random Fields. Foundations and Trends in Machine Learning, 2012, vol. 4(4), p. 267–373. DOI: 10.1561/2200000013</mixed-citation><mixed-citation xml:lang="en">Abidov A., Mirzaev T. UzBERT: A Pretrained Language Model for Uzbek // Technical Report, Tashkent University of Information Technologies. – 2022. – 25 p. URL: https://archive.org/details/uzbert-report</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Jiao X., Yin Y., Shang L., Jiang X., Chen X., Li L., Wang F., Liu Q. TinyBERT: Distilling BERT for Natural Language Understanding, arXiv preprint arXiv:1909.10351, 2019, URL: https://arxiv.org/abs/1909.10351</mixed-citation><mixed-citation xml:lang="en">Sutton C., McCallum A. An Introduction to Conditional Random Fields // Foundations and Trends in Machine Learning. – 2012. – Vol. 4(4). – P. 267–373. DOI: 10.1561/2200000013</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Sanh V., Debut L., Chaumond J., Wolf T. DistilBERT, a Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter, arXiv preprint arXiv:1910.01108, 2019, URL: https://arxiv.org/abs/1910.01108</mixed-citation><mixed-citation xml:lang="en">Jiao X., Yin Y., Shang L., Jiang X., Chen X., Li L., Wang F., Liu Q. TinyBERT: Distilling BERT for Natural Language Understanding arXiv preprint arXiv:1909.10351. 2019. URL: https://arxiv.org/abs/1909.10351</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Rakhimov S., Khamidov J. Development of a Morphological Analyzer for Uzbek. Journal of Natural Language Engineering, 2021, vol. 27(3), p. 311–328. DOI: 10.1017/S1351324921000047</mixed-citation><mixed-citation xml:lang="en">Sanh V., Debut L., Chaumond J., Wolf T. DistilBERT, a Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter arXiv preprint arXiv:1910.01108. 2019. URL: https://arxiv.org/abs/1910.01108</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Rasulov A., Karimov J. Building a Corpus for Low-Resource Languages: A Case Study on Uzbek. LREC, 2022, p. 112–119. URL: https://aclanthology.org/2022.lrec-1.12</mixed-citation><mixed-citation xml:lang="en">Rakhimov S., Khamidov J. Development of a Morphological Analyzer for Uzbek // Journal of Natural Language Engineering. – 2021. – Vol. 27(3). – P. 311–328. DOI: 10.1017/S1351324921000047</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Rasulov A., Karimov J. Building a Corpus for Low-Resource Languages: A Case Study on Uzbek // Proceedings of LREC. – 2022. – P. 112–119. URL: https://aclanthology.org/2022.lrec-1.12</mixed-citation><mixed-citation xml:lang="en">Rasulov A., Karimov J. Building a Corpus for Low-Resource Languages: A Case Study on Uzbek // Proceedings of LREC. – 2022. – P. 112–119. URL: https://aclanthology.org/2022.lrec-1.12</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>
