<?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">mais</journal-id><journal-title-group><journal-title xml:lang="ru">Моделирование и анализ информационных систем</journal-title><trans-title-group xml:lang="en"><trans-title>Modeling and Analysis of Information Systems</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1818-1015</issn><issn pub-type="epub">2313-5417</issn><publisher><publisher-name>Yaroslavl State University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.18255/1818-1015-2026-1-62-77</article-id><article-id custom-type="elpub" pub-id-type="custom">mais-2003</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>Artificial Intelligence</subject></subj-group></article-categories><title-group><article-title>Влияние размера обучающей выборки на качество автоматической оценки коротких ответов</article-title><trans-title-group xml:lang="en"><trans-title>The impact of the size of training sets on quality of automatic short answers grading</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0000-9551-6007</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Рогулин</surname><given-names>Лев Сергеевич</given-names></name><name name-style="western" xml:lang="en"><surname>Rogulin</surname><given-names>Lev S.</given-names></name></name-alternatives><email xlink:type="simple">rogulev0805@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/0000-0003-0116-4739</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Полетаев</surname><given-names>Анатолий Юрьевич</given-names></name><name name-style="western" xml:lang="en"><surname>Poletaev</surname><given-names>Anatoliy Y.</given-names></name></name-alternatives><email xlink:type="simple">anatoliy-poletaev@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/0000-0002-1742-3240</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Лагутина</surname><given-names>Ксения Владимировна</given-names></name><name name-style="western" xml:lang="en"><surname>Lagutina</surname><given-names>Ksenia V.</given-names></name></name-alternatives><email xlink:type="simple">lagutinakv@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Ярославский государственный университет им. П.Г. Демидова</institution><country>Россия</country></aff><aff xml:lang="en"><institution>P.G. Demidov Yaroslavl State University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>16</day><month>03</month><year>2026</year></pub-date><volume>33</volume><issue>1</issue><fpage>62</fpage><lpage>77</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Рогулин Л.С., Полетаев А.Ю., Лагутина К.В., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Рогулин Л.С., Полетаев А.Ю., Лагутина К.В.</copyright-holder><copyright-holder xml:lang="en">Rogulin L.S., Poletaev A.Y., Lagutina K.V.</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://www.mais-journal.ru/jour/article/view/2003">https://www.mais-journal.ru/jour/article/view/2003</self-uri><abstract><p>В работе исследуется влияние объёма обучающей выборки на качество автоматического оценивания правильности коротких ответов, представленного в виде задачи классификации. Влияние оценивалось на примере метода, основанного на оценке сходства между оцениваемым ответом и заданным эталонным ответом, рассчитываемого с помощью векторов эмбеддингов, и классификатора на основе логистической регрессии. Эксперименты проводились на корпусах ответов студентов на вопросы по компьютерным наукам, истории и разработке на Qt. Объём корпусов составил 547, 522 и 931 ответ соответственно. В ходе выполнения работы было поставлено два эксперимента. В ходе первого эксперимента оценивалось изменение качества классификации при уменьшении объёма обучающей выборки. Он показал, что при бинарной классификации (когда ответ может быть либо верным, либо неверным) уменьшение объёма обучающей выборки классификатора приводит к меньшему снижению качества, чем при тернарной классификации (когда выделяется класс частично верных ответов). В ходе второго эксперимента изучалась возможность повышения качества классификации за счёт расширения обучающей выборки малого объёма с помощью аугментации. Он показал, что аугментация, выполненная с помощью генеративной модели DeepSeek, позволяет в ряде случаев значительно улучшить результат, что представляется важным для практического применения в условиях дефицита данных. Также в ходе экспериментов было выявлено, что при использовании для генерации эмбеддингов различных языковых моделей величина изменения качества классификации при изменении объёма обучающей выборки может существенно различаться: при использовании некоторых для получения эмбеддингов моделей rubert-tiny2 и MiniLM-L12-v2 результаты оказываются более стабильными, чем при использовании других моделей.</p></abstract><trans-abstract xml:lang="en"><p>The paper investigates the impact of training set size on the quality of automatic short answers grading, formulated as a classification task. The impact was evaluated using a method based on measuring the similarity between the assessed answer and a given reference answer, calculated via embedding vectors, in combination with a logistic regression classifier. Experiments were conducted on corpora of answers to questions in computer science, history, and software development using Qt framework. The sizes of the corpora were 547, 522, and 931 answers, respectively. Two experiments were conducted during the study. In the first experiment, the change in classification quality was assessed as the training set size was reduced. It showed that when the binary classification is utilized (an answer can be either correct or incorrect), reducing the size of the training set leads to a smaller decline in quality compared to ternary classification (which includes a class of partially correct answers). In the second experiment, the possibility of improving classification quality by expanding small‑sized training sets through data augmentation was investigated. It demonstrated that augmentation performed using the DeepSeek generative model can significantly improve results in several cases, which is important for practical applications under data scarcity conditions. Additionally, the experiments revealed that when different language models are used to generate embeddings, the magnitude of change in classification quality with varying training set sizes can differ significantly. Specifically, using certain models — such as rubert‑tiny2 and MiniLM‑L12‑v2 — to produce embeddings yields more stable results than using other models.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>автоматическая оценка коротких ответов</kwd><kwd>аугментация данных</kwd><kwd>классификация текстов</kwd><kwd>нейросетевые языковые модели</kwd><kwd>оценка открытых ответов учащихся</kwd><kwd>искусственный интеллект в образовании</kwd></kwd-group><kwd-group xml:lang="en"><kwd>ASAG</kwd><kwd>data augmentation</kwd><kwd>text classification</kwd><kwd>neural network language models</kwd><kwd>assessing students' open responses</kwd><kwd>artificial intelligence in education</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">ЯрГУ (проект VIP-021)</funding-statement><funding-statement xml:lang="en">Yaroslavl State University (project VIP-021)</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">R. Gao, H. E. Merzdorf, S. Anwar, M. C. Hipwell, and A. R. Srinivasa, “Automatic assessment of text-based responses in post-secondary education: A systematic review,” Computers and Education: Artificial Intelligence, vol. 6, p. 100206, 2024, doi: 10.1016/j.caeai.2024.100206.</mixed-citation><mixed-citation xml:lang="en">R. Gao, H. E. Merzdorf, S. Anwar, M. C. Hipwell, and A. R. Srinivasa, “Automatic assessment of text-based responses in post-secondary education: A systematic review,” Computers and Education: Artificial Intelligence, vol. 6, p. 100206, 2024, doi: 10.1016/j.caeai.2024.100206.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">N. S. Lagutina and K. V. Lagutina, “A Survey of Models for Automatic Assessment of Similarity of Student’s Answer to the Reference Answer,” Automatic Control and Computer Sciences, vol. 59, no. 7, pp. 1152–1169, 2025, doi: 10.3103/S0146411625700427.</mixed-citation><mixed-citation xml:lang="en">N. S. Lagutina and K. V. Lagutina, “A Survey of Models for Automatic Assessment of Similarity of Student’s Answer to the Reference Answer,” Automatic Control and Computer Sciences, vol. 59, no. 7, pp. 1152–1169, 2025, doi: 10.3103/S0146411625700427.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">S. Kumar, S. Chakrabarti, and S. Roy, “Earth mover's distance pooling over Siamese LSTMs for automatic short answer grading,” in Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017, pp. 2046–2052, doi: 10.24963/ijcai.2017/284.</mixed-citation><mixed-citation xml:lang="en">S. Kumar, S. Chakrabarti, and S. Roy, “Earth mover's distance pooling over Siamese LSTMs for automatic short answer grading,” in Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017, pp. 2046–2052, doi: 10.24963/ijcai.2017/284.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">T. H. Nguyen, H. H. Nguyen, Z. Ahmadi, T.-A. Hoang, and T.-N. Doan, “On the impact of dataset size: A Twitter classification case study,” in IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, 2021, pp. 210–217, doi: 10.1145/3486622.3493960.</mixed-citation><mixed-citation xml:lang="en">T. H. Nguyen, H. H. Nguyen, Z. Ahmadi, T.-A. Hoang, and T.-N. Doan, “On the impact of dataset size: A Twitter classification case study,” in IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, 2021, pp. 210–217, doi: 10.1145/3486622.3493960.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">A. R. Nair, R. P. Singh, D. Gupta, and P. Kumar, “Evaluating the impact of text data augmentation on text classification tasks using DistilBERT,” Procedia Computer Science, vol. 235, pp. 102–111, 2024, doi: 10.1016/j.procs.2024.04.013.</mixed-citation><mixed-citation xml:lang="en">A. R. Nair, R. P. Singh, D. Gupta, and P. Kumar, “Evaluating the impact of text data augmentation on text classification tasks using DistilBERT,” Procedia Computer Science, vol. 235, pp. 102–111, 2024, doi: 10.1016/j.procs.2024.04.013.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">C. Shorten, T. M. Khoshgoftaar, and B. Furht, “Text data augmentation for deep learning,” Journal of Big Data, vol. 8, p. 101, 2021, doi: 10.1186/s40537-021-00492-0.</mixed-citation><mixed-citation xml:lang="en">C. Shorten, T. M. Khoshgoftaar, and B. Furht, “Text data augmentation for deep learning,” Journal of Big Data, vol. 8, p. 101, 2021, doi: 10.1186/s40537-021-00492-0.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">A. Poulton and S. Eliens, “Explaining transformer-based models for automatic short answer grading,” in Proceedings of the 5th International Conference on Digital Technology in Education, 2021, pp. 110–116, doi: 10.1145/3488466.3488479.</mixed-citation><mixed-citation xml:lang="en">A. Poulton and S. Eliens, “Explaining transformer-based models for automatic short answer grading,” in Proceedings of the 5th International Conference on Digital Technology in Education, 2021, pp. 110–116, doi: 10.1145/3488466.3488479.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">G. Kortemeyer, “Performance of the pre-trained large language model GPT-4 on automated short answer grading,” Discover Artificial Intelligence, vol. 4, no. 1, p. 47, 2024, doi: 10.1007/s44163-024-00147-y.</mixed-citation><mixed-citation xml:lang="en">G. Kortemeyer, “Performance of the pre-trained large language model GPT-4 on automated short answer grading,” Discover Artificial Intelligence, vol. 4, no. 1, p. 47, 2024, doi: 10.1007/s44163-024-00147-y.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">C. B. Minnegalieva, I. I. Kashapov, and O. D. Morozova, “Automated Grading of Students’ Short Answers Using Language Models,” Automatic Documentation and Mathematical Linguistics, vol. 58, no. Suppl 3, pp. S109–S114, 2024, doi: 10.3103/S0005105525700177.</mixed-citation><mixed-citation xml:lang="en">C. B. Minnegalieva, I. I. Kashapov, and O. D. Morozova, “Automated Grading of Students’ Short Answers Using Language Models,” Automatic Documentation and Mathematical Linguistics, vol. 58, no. Suppl 3, pp. S109–S114, 2024, doi: 10.3103/S0005105525700177.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">H. Tan, C. Wang, Q. Duan, Y. Lu, H. Zhang, and R. Li, “Automatic short answer grading by encoding student responses via a graph convolutional network,” Interactive Learning Environments, vol. 31, no. 3, pp. 1636–1650, 2023, doi: 10.1080/10494820.2020.1855207.</mixed-citation><mixed-citation xml:lang="en">H. Tan, C. Wang, Q. Duan, Y. Lu, H. Zhang, and R. Li, “Automatic short answer grading by encoding student responses via a graph convolutional network,” Interactive Learning Environments, vol. 31, no. 3, pp. 1636–1650, 2023, doi: 10.1080/10494820.2020.1855207.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">J. Lun, J. Zhu, Y. Tang, and M. Yang, “Multiple data augmentation strategies for improving performance on automatic short answer scoring,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2020, vol. 34, no. 09, pp. 13389–13396, doi: 10.1609/aaai.v34i09.7062.</mixed-citation><mixed-citation xml:lang="en">J. Lun, J. Zhu, Y. Tang, and M. Yang, “Multiple data augmentation strategies for improving performance on automatic short answer scoring,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2020, vol. 34, no. 09, pp. 13389–13396, doi: 10.1609/aaai.v34i09.7062.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">M. C. Wijanto and H.-S. Yong, “Combining balancing dataset and SentenceTransformers to improve short answer grading performance,” Applied Sciences, vol. 14, no. 11, p. 4532, 2024, doi: 10.3390/app14114532.</mixed-citation><mixed-citation xml:lang="en">M. C. Wijanto and H.-S. Yong, “Combining balancing dataset and SentenceTransformers to improve short answer grading performance,” Applied Sciences, vol. 14, no. 11, p. 4532, 2024, doi: 10.3390/app14114532.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">S. Zhong, J. Zeng, Y. Yu, and B. Lin, “Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs,” International Journal of Data Science and Analytics, vol. 20, pp. 5377–5398, 2025, doi: 10.1007/s41060-025-00774-3.</mixed-citation><mixed-citation xml:lang="en">S. Zhong, J. Zeng, Y. Yu, and B. Lin, “Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs,” International Journal of Data Science and Analytics, vol. 20, pp. 5377–5398, 2025, doi: 10.1007/s41060-025-00774-3.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">R. Li et al., “Retrieval-augmented meta learning for low-resource text classification,” in Proceedings of the International Joint Conference on Neural Networks, 2024, pp. 1–8, doi: 10.1109/IJCNN60899.2024.10651119.</mixed-citation><mixed-citation xml:lang="en">R. Li et al., “Retrieval-augmented meta learning for low-resource text classification,” in Proceedings of the International Joint Conference on Neural Networks, 2024, pp. 1–8, doi: 10.1109/IJCNN60899.2024.10651119.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Y. Yu, Y. Zhuang, R. Zhang, Y. Meng, J. Shen, and C. Zhang, “ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval,” in Findings of the Association for Computational Linguistics: ACL 2023, 2023, pp. 11782–11805, doi: 10.18653/v1/2023.findings-acl.748.</mixed-citation><mixed-citation xml:lang="en">Y. Yu, Y. Zhuang, R. Zhang, Y. Meng, J. Shen, and C. Zhang, “ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval,” in Findings of the Association for Computational Linguistics: ACL 2023, 2023, pp. 11782–11805, doi: 10.18653/v1/2023.findings-acl.748.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">H. Dai et al., “AugGPT: Leveraging ChatGPT for Text Data Augmentation,” IEEE Transactions on Big Data, vol. 11, pp. 907–918, 2025, doi: 10.1109/TBDATA.2025.3536934.</mixed-citation><mixed-citation xml:lang="en">H. Dai et al., “AugGPT: Leveraging ChatGPT for Text Data Augmentation,” IEEE Transactions on Big Data, vol. 11, pp. 907–918, 2025, doi: 10.1109/TBDATA.2025.3536934.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">V. N. Kopnin and N. S. Lagutina, “Analysis of the Application of Large Language Models for Comparing Open Student Responses with Reference Answers,” in Matematicheskoe i Informacionnoe Modelirovanie: Materialy Vserossijskoj Konferencii Molodyh Uchenyh, 2025, vol. 23.</mixed-citation><mixed-citation xml:lang="en">V. N. Kopnin and N. S. Lagutina, “Analysis of the Application of Large Language Models for Comparing Open Student Responses with Reference Answers,” in Matematicheskoe i Informacionnoe Modelirovanie: Materialy Vserossijskoj Konferencii Molodyh Uchenyh, 2025, vol. 23.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">A. Liu et al., “DeepSeek-V3 Technical Report.” 2025, doi: 10.48550/arXiv.2412.19437v2.</mixed-citation><mixed-citation xml:lang="en">A. Liu et al., “DeepSeek-V3 Technical Report.” 2025, doi: 10.48550/arXiv.2412.19437v2.</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>
