<?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">ntv</journal-id><journal-title-group><journal-title xml:lang="ru">Научно-технический вестник информационных технологий, механики и оптики</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific and Technical Journal of Information Technologies, Mechanics and Optics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2226-1494</issn><issn pub-type="epub">2500-0373</issn><publisher><publisher-name>Университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/2226-1494-2026-26-2-337-348</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-596</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>КОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>COMPUTER SCIENCE</subject></subj-group></article-categories><title-group><article-title>Многозадачный анализ психологического портрета человека на основе текстовых данных с применением полуконтролируемого обучения</article-title><trans-title-group xml:lang="en"><trans-title>Multi-task human’s psychological profile analysis based on text data using semi-supervised learning</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0009-6207-8413</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Коряковская</surname><given-names>Д. О.</given-names></name><name name-style="western" xml:lang="en"><surname>Koryakovskaya</surname><given-names>D. O.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Коряковская Дарья Олеговна — стажер-исследователь</p><p>Санкт-Петербург, 199178</p></bio><bio xml:lang="en"><p>Darya O. Koryakovskaya — Intern Researcher</p><p>Saint Petersburg, 199178</p></bio><email xlink:type="simple">da.koryakovskaya@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/0000-0002-7479-2851</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Аксёнов</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Axyonov</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Аксёнов Александр Александрович — кандидат технических наук, старший научный сотрудник</p><p>Санкт-Петербург, 199178</p><p>sc 57203963345</p></bio><bio xml:lang="en"><p>Alexandr A. Axyonov — PhD, Senior Researcher</p><p>Saint Petersburg, 199178</p><p>sc 57203963345</p></bio><email xlink:type="simple">a.aksenov95@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/0000-0002-4135-6949</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Рюмина</surname><given-names>Е. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Ryumina</surname><given-names>E. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Рюмина Елена Витальевна — кандидат технических наук, младший научный сотрудник</p><p>Санкт-Петербург, 199178</p><p>sc 57220572427</p></bio><bio xml:lang="en"><p>Elena V. Ryumina — PhD, Junior Researcher</p><p>Saint Petersburg, 199178</p><p>sc 57220572427</p></bio><email xlink:type="simple">ryumina_ev@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/0000-0002-7935-0569</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Рюмин</surname><given-names>Д. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Ryumin</surname><given-names>D. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Рюмин Дмитрий Александрович — кандидат технических наук, старший научный сотрудник</p><p>Санкт-Петербург, 199178</p><p>sc 57191960214</p></bio><bio xml:lang="en"><p>Dmitry A. Ryumin — PhD, Senior Researcher</p><p>Saint Petersburg, 199178</p><p>sc 57191960214</p></bio><email xlink:type="simple">dl_03.03.1991@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Санкт-Петербургский Федеральный исследовательский центр Российской академии наук</institution><country>Россия</country></aff><aff xml:lang="en"><institution>St. Petersburg Federal Research Center of the Russian Academy of Sciences</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>20</day><month>04</month><year>2026</year></pub-date><volume>26</volume><issue>2</issue><fpage>337</fpage><lpage>348</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Коряковская Д.О., Аксёнов А.А., Рюмина Е.В., Рюмин Д.А., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Коряковская Д.О., Аксёнов А.А., Рюмина Е.В., Рюмин Д.А.</copyright-holder><copyright-holder xml:lang="en">Koryakovskaya D.O., Axyonov A.A., Ryumina E.V., Ryumin D.A.</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://ntv.elpub.ru/jour/article/view/596">https://ntv.elpub.ru/jour/article/view/596</self-uri><abstract><p>Введение. Многозадачный анализ психологического портрета человека позволяет формировать более целостное представление о нем, что особенно востребовано в системах персонализации, HR-технологиях и человеко- машинном взаимодействии. Однако до настоящего времени подобные исследования не проводились из-за отсутствия корпусов с совместной разметкой по обеим задачам, что делает невозможным традиционное многозадачное обучение. Метод. Предложен метод полуконтролируемого кросс-доменного обучения, позволяющий эффективно интегрировать два раздельно аннотированных корпуса: CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) (для распознавания эмоций) и ChaLearn First Impressions v2 (FIv2) (для оценивания личностных характеристик), без дополнительной разметки. Экспериментальная установка включает два этапа: обучение независимых однозадачных моделей для извлечения доменно-специфичных признаков и формирование базовых прогнозов; создание совместной кросс-доменной модели с блоками перекрестного внимания, которая объединяет эмоциональные и личностные признаки. Финальное предсказание формируется путем усреднения выходов однозадачных и совместной моделей, что повышает робастность. Выполнено сравнение предобученных энкодеров (Jina-v3 и BGE-en) и контекстных моделей (трансформер и Mamba). Обучение моделей осуществлено с использованием гибридной функции потерь, сочетающей контролируемые и полуконтролируемые компоненты с псевдометками. Основные результаты. Эксперименты показали, что наилучшие результаты достигаются при использовании энкодера Jina-v3 и контекстной модели Mamba: средняя взвешенная точность классификации (mWACC) составила 62,52 %, а средняя взвешенная F1-мера (mMF1) — 61,03 % на корпусе CMU-MOSEI; средняя точность (mACC) составила 88,80 %, а средний коэффициент корреляции конкордации Лина (mCCC) — 25,44 % на FIv2. Модель демонстрирует устойчивую передачу знаний между задачами и превосходит современные решения. Визуализация внимания методом Gradient-weighted Class Activation Mapping подтверждает интерпретируемость прогнозов. Обсуждение. Представленные результаты исследования открывают возможности разработки масштабируемых систем психологического профилирования по тексту в условиях дефицита разметки. Предложенный метод применим в кадровом менеджменте, адаптивных обучающих платформах, персонализированных чат-ботах и цифровой психометрике, где требуются одновременный учет эмоционального состояния и устойчивых личностных характеристик.</p></abstract><trans-abstract xml:lang="en"><p>Multi-task analysis of a human’s psychological profile enables a more holistic representation of the individual, which is particularly valuable in personalization systems, HR technologies, and human–Artificial Intelligence interaction. However, such studies have not been conducted to date due to the lack of datasets jointly annotated for both emotion and personality traits, rendering conventional multi-task learning infeasible. We propose a semi-supervised cross-domain learning method that effectively integrates two separately annotated corpora, CMU-MOSEI (for emotion recognition) and ChaLearn First Impressions v2 (FIv2) (for personality trait assessment), without requiring additional labeling. The experimental setup comprises two stages: first, independent single-task models are trained to extract domain-specific features and generate baseline predictions; second, a joint cross-domain model with cross-attention blocks fuses emotional and personality-related representations. Final predictions are obtained by averaging the outputs of the singletask and joint models, enhancing robustness. We compare pre-trained encoders (Jina-v3 and BGE-en) and contextual decoders (Transformer and Mamba), using a hybrid loss function that combines supervised and semi-supervised components with confidence-based pseudo-labeling. Experiments show that the best performance is achieved with the Jina-v3 encoder and the Mamba contextual model: mWACC = 62.52 % (Mean Weighted Accuracy Classification) and mMF1 = 61.03 % (Mean Weighted F1-Measure) on CMU-MOSEI (Multimodal Opinion Sentiment and Emotion Intensity) corpus; mACC = 88.80 % (Mean Accuracy) and mCCC = 25.44 % (Mean Concordation Correlation Coefficient) on FIv2. The model demonstrates stable knowledge transfer across tasks and outperforms current state-ofthe- art methods. Attention visualization via Grad-CAM confirms the interpretability of predictions. The proposed method enables the development of scalable text-based psychological profiling systems under realistic annotation scarcity. It is applicable in recruitment, adaptive learning platforms, personalized chatbots, and computational psychometrics where simultaneous consideration of emotional states and stable personality traits is essential.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>распознавание эмоций</kwd><kwd>распознавание личностных характеристик</kwd><kwd>многозадачное обучение</kwd><kwd>кросс-доменное машинное обучение</kwd><kwd>полуконтролируемое машинное обучение</kwd><kwd>визуализации внимания модели</kwd></kwd-group><kwd-group xml:lang="en"><kwd>emotion recognition</kwd><kwd>personality trait recognition</kwd><kwd>multitask learning</kwd><kwd>cross-domain learning</kwd><kwd>semi-supervised learning</kwd><kwd>model attention visualization</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Раздел «Обзор литературы» выполнен в рамках бюджетной темы СПб ФИЦ РАН (№ FFZF-2025-0003), разработка компонентов полуконтролируемого машинного обучения, включая гибридную функцию потерь и механизм псевдометок, проведена при поддержке Российского научного фонда (проект № 24-71-00083), а проектирование архитектуры кросс-доменной модели с блоками перекрестного внимания и интеграцией контекстных моделей — при поддержке Российского научного фонда (проект № 24-71-00112).</funding-statement><funding-statement xml:lang="en">The “Related work” was prepared within the framework of the budget topic of the St. Petersburg Federal Research Center of the Russian Academy of Sciences (No. FFZF-2025-0003). The development of semi-supervised machine learning components, including a hybrid loss function and a pseudo-labeling mechanism, was supported by the Russian Science Foundation (project No. 24-71-00083). The design of the cross-domain model architecture featuring cross-attention blocks and integration of contextual models was supported by the Russian Science Foundation (project No. 24‑71‑00112).</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">Karanatsiou D., Sermpezis P., Gruda D., Kafetsios K., Dimitriadis I., Vakali A. My tweets bring all the traits to the yard: Predicting personality and relational traits in Online Social Networks // ACM Transactions on the Web (TWEB). 2022. V. 16. N 2. P. 1–26. https://doi.org/10.1145/3523749</mixed-citation><mixed-citation xml:lang="en">Karanatsiou D., Sermpezis P., Gruda D., Kafetsios K., Dimitriadis I., Vakali A. My tweets bring all the traits to the yard: Predicting personality and relational traits in Online Social Networks // ACM Transactions on the Web (TWEB). 2022. V. 16. N 2. P. 1–26. https://doi.org/10.1145/3523749</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Двойникова А.А, Маркитантов М.В., Рюмина Е.В., Уздяев М.Ю., Величко А.Н., Рюмин Д.А., Ляксо Е.Е., Карпов А.А. Анализ информационного и математического обеспечения для распознавания аффективных состояний человека // Информатика и автоматизация. 2022. Т. 21. № 6. С. 1097–1144. https://doi.org/10.15622/ia.21.6.2</mixed-citation><mixed-citation xml:lang="en">Dvoynikova A.A., Markitantov M.V., Ryumina E.V., Uzdiaev M.Y., Velichko A.N., Ryumin D.A., et al. Analysis of infoware and software for human affective states recognition. Informatics and Automation, 2022, vol. 21, no. 6. pp. 1097–1144. (in Russian). https://doi.org/10.15622/ia.21.6.2</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Sorin V., Brin D., Barash Y., Konen E., Charney A., Nadkarni G., Klang E. Large language models and empathy: systematic review // Journal of Medical Internet Research. 2024. V. 26. P. e52597. https://doi.org/10.2196/52597</mixed-citation><mixed-citation xml:lang="en">Sorin V., Brin D., Barash Y., Konen E., Charney A., Nadkarni G., Klang E. Large language models and empathy: systematic review // Journal of Medical Internet Research. 2024. V. 26. P. e52597. https://doi.org/10.2196/52597</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Rajesh S.G., Madangarli S.V., Pisharady G.S., Subrahmanyam R. Enhancement of Virtual Assistants through MultiModal AI for Emotion Recognition // IEEE Access. 2025. V. 13. P. 102159–102179. https://doi.org/10.1109/ACCESS.2025.3577664</mixed-citation><mixed-citation xml:lang="en">Rajesh S.G., Madangarli S.V., Pisharady G.S., Subrahmanyam R. Enhancement of Virtual Assistants through MultiModal AI for Emotion Recognition // IEEE Access. 2025. V. 13. P. 102159–102179. https://doi.org/10.1109/ACCESS.2025.3577664</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Kovacevic N., Holz C., Gross M., Wampfler R. On multimodal emotion recognition for human-chatbot interaction in the wild // Proc. of the International Conference on Multimodal Interaction. 2024. P. 12–21. https://doi.org/10.1145/3678957.3685759</mixed-citation><mixed-citation xml:lang="en">Kovacevic N., Holz C., Gross M., Wampfler R. On multimodal emotion recognition for human-chatbot interaction in the wild // Proc. of the International Conference on Multimodal Interaction. 2024. P. 12–21. https://doi.org/10.1145/3678957.3685759</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Bao Y., Wang Y., Qi Y., Yang Q., Liu R., Feng L. Emotion-Assisted multi-modal Personality Recognition using adversarial Contrastive learning // Knowledge-Based Systems. 2025. V. 317. P. 113504. https://doi.org/10.1016/j.knosys.2025.113504</mixed-citation><mixed-citation xml:lang="en">Bao Y., Wang Y., Qi Y., Yang Q., Liu R., Feng L. Emotion-Assisted multi-modal Personality Recognition using adversarial Contrastive learning // Knowledge-Based Systems. 2025. V. 317. P. 113504. https://doi.org/10.1016/j.knosys.2025.113504</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Mohammadi G., Vuilleumier P. A multi-componential approach to emotion recognition and the effect of personality // IEEE Transactions on Affective Computing. 2020. V. 13. N 3. P. 1127–1139. https://doi.org/10.1109/TAFFC.2020.3028109</mixed-citation><mixed-citation xml:lang="en">Mohammadi G., Vuilleumier P. A multi-componential approach to emotion recognition and the effect of personality // IEEE Transactions on Affective Computing. 2020. V. 13. N 3. P. 1127–1139. https://doi.org/10.1109/TAFFC.2020.3028109</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Li Y., Bell P., Lai C. Transfer Learning for Personality Perception via Speech Emotion Recognition // Proc. of the Annual Conference of the International Speech Communication Association Interspeech. 2023. P. 5197–5201. https://doi.org/10.21437/Interspeech.2023-2061</mixed-citation><mixed-citation xml:lang="en">Li Y., Bell P., Lai C. Transfer Learning for Personality Perception via Speech Emotion Recognition // Proc. of the Annual Conference of the International Speech Communication Association Interspeech. 2023. P. 5197–5201. https://doi.org/10.21437/Interspeech.2023-2061</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Chandraumakantham O., Gowtham N., Zakariah M., Almazyad A. Multimodal emotion recognition using feature fusion: an LLM-based approach // IEEE Access. 2024. V. 12. P. 108052–108071. https://doi.org/10.1109/ACCESS.2024.3425953</mixed-citation><mixed-citation xml:lang="en">Chandraumakantham O., Gowtham N., Zakariah M., Almazyad A. Multimodal emotion recognition using feature fusion: an LLM-based approach // IEEE Access. 2024. V. 12. P. 108052–108071. https://doi.org/10.1109/ACCESS.2024.3425953</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Gan P., Sowmya A., Mohammadi G. CLIP-based model for effective and explainable apparent personality perception // Proc. of the 1st International Workshop on Multimodal and Responsible A f f e c t i v e Computing. 2023. P. 29–37. https://doi.org/10.1145/3607865.3613178</mixed-citation><mixed-citation xml:lang="en">Gan P., Sowmya A., Mohammadi G. CLIP-based model for effective and explainable apparent personality perception // Proc. of the 1st International Workshop on Multimodal and Responsible Affective Computing. 2023. P. 29–37. https://doi.org/10.1145/3607865.3613178</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding // Proc. of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2019. V. 1. P. 4171–4186. https://doi.org/10.18653/v1/N19-1423</mixed-citation><mixed-citation xml:lang="en">Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding // Proc. of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2019. V. 1. P. 4171–4186. https://doi.org/10.18653/v1/N19-1423</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Boitel E., Mohasseb A., Haig E. MIST: Multimodal emotion recognition using DeBERTa for text, Semi-CNN for speech, ResNet-50 for facial, and 3D-CNN for motion analysis // Expert Systems with Applications. 2025. V. 270. P. 126236. https://doi.org/10.1016/j.eswa.2024.126236</mixed-citation><mixed-citation xml:lang="en">Boitel E., Mohasseb A., Haig E. MIST: Multimodal emotion recognition using DeBERTa for text, Semi-CNN for speech, ResNet-50 for facial, and 3D-CNN for motion analysis // Expert Systems with Applications. 2025. V. 270. P. 126236. https://doi.org/10.1016/j.eswa.2024.126236</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Li Y., Wang Y., Cui Z. Decoupled multimodal distilling for emotion recognition // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023. P. 6631–6640. https://doi.org/10.1109/CVPR52729.2023.00641</mixed-citation><mixed-citation xml:lang="en">Li Y., Wang Y., Cui Z. Decoupled multimodal distilling for emotion recognition // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023. P. 6631–6640. https://doi.org/10.1109/CVPR52729.2023.00641</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Agrawal T., Balazia M., Müller P., Brémond F. Multimodal vision transformers with forced attention for behavior analysis // Proc. of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2023. P. 3381–3391. https://doi.org/10.1109/WACV56688.2023.00339</mixed-citation><mixed-citation xml:lang="en">Agrawal T., Balazia M., Müller P., Brémond F. Multimodal vision transformers with forced attention for behavior analysis // Proc. of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2023. P. 3381–3391. https://doi.org/10.1109/WACV56688.2023.00339</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Ryumina E., Markitantov M., Ryumin D., Karpov A. Gated Siamese Fusion Network based on multimodal deep and hand-crafted features for personality traits assessment // Pattern Recognition Letters. 2024. V. 185. P. 45–51. https://doi.org/10.1016/j.patrec.2024.07.004</mixed-citation><mixed-citation xml:lang="en">Ryumina E., Markitantov M., Ryumin D., Karpov A. Gated Siamese Fusion Network based on multimodal deep and hand-crafted features for personality traits assessment // Pattern Recognition Letters. 2024. V. 185. P. 45–51. https://doi.org/10.1016/j.patrec.2024.07.004</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Peng C., Chen K., Shou L., Chen G. CARAT: Contrastive feature reconstruction and aggregation for multi-modal multi-label emotion recognition // Proceedings of the AAAI Conference on Artificial Intelligence. 2024. V. 38. N 13. P. 14581–14589. https://doi.org/10.1609/aaai.v38i13.29374</mixed-citation><mixed-citation xml:lang="en">Peng C., Chen K., Shou L., Chen G. CARAT: Contrastive feature reconstruction and aggregation for multi-modal multi-label emotion recognition // Proceedings of the AAAI Conference on Artificial Intelligence. 2024. V. 38. N 13. P. 14581–14589. https://doi.org/10.1609/aaai.v38i13.29374</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Bagher Zadeh A., Liang P.P., Poria S., Cambria E., Morency L.P. Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph // Proc. of the 56th Annual Meeting of the Association for Computational Linguistics. 2018. V. 1. P. 2236–2246. https://doi.org/10.18653/v1/P18-1208</mixed-citation><mixed-citation xml:lang="en">Bagher Zadeh A., Liang P.P., Poria S., Cambria E., Morency L.P. Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph // Proc. of the 56th Annual Meeting of the Association for Computational Linguistics. 2018. V. 1. P. 2236–2246. https://doi.org/10.18653/v1/P18-1208</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Escalante H.J., Kaya H., Salah A., Escalera S., Gucluturk Y., Guclu U., et al. Modeling, Recognizing, and Explaining Apparent Personality from Videos // IEEE Transactions on Affective Computing. 2020. V. 13. N 2. P. 894–911. https://doi.org/10.1109/TAFFC.2020.2973984</mixed-citation><mixed-citation xml:lang="en">Escalante H.J., Kaya H., Salah A., Escalera S., Gucluturk Y., Guclu U., et al. Modeling, Recognizing, and Explaining Apparent Personality from Videos // IEEE Transactions on Affective Computing. 2020. V. 13. N 2. P. 894–911. https://doi.org/10.1109/TAFFC.2020.2973984</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Ouali Y., Hudelot C., Tami M. Semi-supervised semantic segmentation with cross-consistency training // Proc. of the IEEE/ CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020. P. 12671–12681. https://doi.org/10.1109/CVPR42600.2020.01269</mixed-citation><mixed-citation xml:lang="en">Ouali Y., Hudelot C., Tami M. Semi-supervised semantic segmentation with cross-consistency training // Proc. of the IEEE/ CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020. P. 12671–12681. https://doi.org/10.1109/CVPR42600.2020.01269</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Lian Z., Liu B., Tao J. SMIN: Semi-supervised multi-modal interaction network for conversational emotion recognition // IEEE Transactions on Affective Computing. 2023. V. 14. N 3. P. 2415– 2429. https://doi.org/10.1109/TAFFC.2022.3141237</mixed-citation><mixed-citation xml:lang="en">Lian Z., Liu B., Tao J. SMIN: Semi-supervised multi-modal interaction network for conversational emotion recognition // IEEE Transactions on Affective Computing. 2023. V. 14. N 3. P. 2415– 2429. https://doi.org/10.1109/TAFFC.2022.3141237</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Conneau A., Khandelwal K., Goyal N., Chaudhary V., Wenzek G., Guzmán F., et al. Unsupervised cross-lingual representation learning at scale // Proc. of the 58th Annual Meeting of the Association for Computational Linguistics. 2020. P. 8440–8451. https://doi.org/10.18653/v1/2020.acl-main.747</mixed-citation><mixed-citation xml:lang="en">Conneau A., Khandelwal K., Goyal N., Chaudhary V., Wenzek G., Guzmán F., et al. Unsupervised cross-lingual representation learning at scale // Proc. of the 58th Annual Meeting of the Association for Computational Linguistics. 2020. P. 8440–8451. https://doi.org/10.18653/v1/2020.acl-main.747</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Hosseini S.S., Yamaghani M.R., Arabani S.P. Multimodal modelling of human emotion using sound, image and text fusion // Signal, Image and Video Processing. 2023. V. 18. N 1. P. 71–79. https://doi.org/10.1007/s11760-023-02707-8</mixed-citation><mixed-citation xml:lang="en">Hosseini S.S., Yamaghani M.R., Arabani S.P. Multimodal modelling of human emotion using sound, image and text fusion // Signal, Image and Video Processing. 2023. V. 18. N 1. P. 71–79. https://doi.org/10.1007/s11760-023-02707-8</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Deng L., Liu B., Li Z. Multimodal sentiment analysis based on a cross-modal multihead attention mechanism // Computers, Materials and Continua. 2024. V. 78. N 1. P. 1157–1170. https://doi.org/10.32604/cmc.2023.042150</mixed-citation><mixed-citation xml:lang="en">Deng L., Liu B., Li Z. Multimodal sentiment analysis based on a cross-modal multihead attention mechanism // Computers, Materials and Continua. 2024. V. 78. N 1. P. 1157–1170. https://doi.org/10.32604/cmc.2023.042150</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Goncalves L., Leem S.-G., Lin W.-C., Sisman B., Busso C. Versatile audio-visual learning for emotion recognition // IEEE Transactions on Affective Computing. 2023. V. 16. N 1. P. 306–318. https://doi.org/10.1109/TAFFC.2024.3433386</mixed-citation><mixed-citation xml:lang="en">Goncalves L., Leem S.-G., Lin W.-C., Sisman B., Busso C. Versatile audio-visual learning for emotion recognition // IEEE Transactions on Affective Computing. 2023. V. 16. N 1. P. 306–318. https://doi.org/10.1109/TAFFC.2024.3433386</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Cui Z., Li Y., Wang Y. Incomplete multimodality-diffused emotion recognition // Proc. of the Advances in Neural Information Processing System. 2023. P. 17117–17128. https://doi.org/10.52202/075280-0748</mixed-citation><mixed-citation xml:lang="en">Cui Z., Li Y., Wang Y. Incomplete multimodality-diffused emotion recognition // Proc. of the Advances in Neural Information Processing System. 2023. P. 17117–17128. https://doi.org/10.52202/075280-0748</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">Arumugam L., Arumugam S., Chidambaram P., Govindasamy K. A multi-modal deep learning approach for human emotion recognition // Cognitive Neurodynamics. 2025. V. 19. N 1. P. 123. https://doi.org/10.1007/s11571-025-10304-3</mixed-citation><mixed-citation xml:lang="en">Arumugam L., Arumugam S., Chidambaram P., Govindasamy K. A multi-modal deep learning approach for human emotion recognition // Cognitive Neurodynamics. 2025. V. 19. N 1. P. 123. https://doi.org/10.1007/s11571-025-10304-3</mixed-citation></citation-alternatives></ref><ref id="cit27"><label>27</label><citation-alternatives><mixed-citation xml:lang="ru">Li D., Xing B., Liu X., Xia B., Wen B., Kälviäinen H. DEEMO: Deidentity multimodal emotion recognition and reasoning // arXiv. 2025. arXiv:2504.19549. https://doi.org/10.48550/arXiv.2504.19549</mixed-citation><mixed-citation xml:lang="en">Li D., Xing B., Liu X., Xia B., Wen B., Kälviäinen H. DEEMO: Deidentity multimodal emotion recognition and reasoning // arXiv. 2025. arXiv:2504.19549. https://doi.org/10.48550/arXiv.2504.19549</mixed-citation></citation-alternatives></ref><ref id="cit28"><label>28</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang D., Ju X., Li J., Li S., Zhu Q., Zhou G. Multi-modal multi-label emotion detection with modality and label dependence // Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020. P. 3584–3593. https://doi.org/10.18653/v1/2020.emnlp-main.291</mixed-citation><mixed-citation xml:lang="en">Zhang D., Ju X., Li J., Li S., Zhu Q., Zhou G. Multi-modal multi-label emotion detection with modality and label dependence // Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020. P. 3584–3593. https://doi.org/10.18653/v1/2020.emnlp-main.291</mixed-citation></citation-alternatives></ref><ref id="cit29"><label>29</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang Y., Chen M., Shen J., Wang C. TAILOR versatile multi-modal learning for multi-label emotion recognition // Proceedings of the AAAI Conference on Artificial Intelligence. 2022. V. 36. N 8. P. 9100–9108. https://doi.org/10.1609/aaai.v36i8.20895</mixed-citation><mixed-citation xml:lang="en">Zhang Y., Chen M., Shen J., Wang C. TAILOR versatile multi-modal learning for multi-label emotion recognition // Proceedings of the AAAI Conference on Artificial Intelligence. 2022. V. 36. N 8. P. 9100–9108. https://doi.org/10.1609/aaai.v36i8.20895</mixed-citation></citation-alternatives></ref><ref id="cit30"><label>30</label><citation-alternatives><mixed-citation xml:lang="ru">Ryumina E., Ryumin D., Axyonov A., Ivanko D., Karpov A. Multicorpus emotion recognition method based on cross-modal gated attention fusion // Pattern Recognition Letters. 2025. V. 190. P. 192– 200. https://doi.org/10.1016/j.patrec.2025.02.024</mixed-citation><mixed-citation xml:lang="en">Ryumina E., Ryumin D., Axyonov A., Ivanko D., Karpov A. Multicorpus emotion recognition method based on cross-modal gated attention fusion // Pattern Recognition Letters. 2025. V. 190. P. 192– 200. https://doi.org/10.1016/j.patrec.2025.02.024</mixed-citation></citation-alternatives></ref><ref id="cit31"><label>31</label><citation-alternatives><mixed-citation xml:lang="ru">Naz A., Khan H.U., Bukhari A., Alshemaimri B., Daud A., Ramzan M. Machine and deep learning for personality traits detection: a comprehensive survey and open research challenges // Artificial Intelligence Review. 2025. V. 58. N 8. P. 239. https://doi.org/10.1007/s10462-025-11245-3</mixed-citation><mixed-citation xml:lang="en">Naz A., Khan H.U., Bukhari A., Alshemaimri B., Daud A., Ramzan M. Machine and deep learning for personality traits detection: a comprehensive survey and open research challenges // Artificial Intelligence Review. 2025. V. 58. N 8. P. 239. https://doi.org/10.1007/s10462-025-11245-3</mixed-citation></citation-alternatives></ref><ref id="cit32"><label>32</label><citation-alternatives><mixed-citation xml:lang="ru">Soto C.J., Jackson J.J. Five-factor model of personality // Journal of Research in Personality. 2013. V. 42. P. 1285–1302.</mixed-citation><mixed-citation xml:lang="en">Soto C.J., Jackson J.J. Five-factor model of personality // Journal of Research in Personality. 2013. V. 42. P. 1285–1302.</mixed-citation></citation-alternatives></ref><ref id="cit33"><label>33</label><citation-alternatives><mixed-citation xml:lang="ru">Ouarka A., Baha T.A., Es-Saady Y., El Hajji M. A deep multimodal fusion method for personality traits prediction // Multimedia Tools and Applications. 2024. V. 84. N 25. P. 29665–29687. https://doi.org/10.1007/s11042-024-20356-y</mixed-citation><mixed-citation xml:lang="en">Ouarka A., Baha T.A., Es-Saady Y., El Hajji M. A deep multimodal fusion method for personality traits prediction // Multimedia Tools and Applications. 2024. V. 84. N 25. P. 29665–29687. https://doi.org/10.1007/s11042-024-20356-y</mixed-citation></citation-alternatives></ref><ref id="cit34"><label>34</label><citation-alternatives><mixed-citation xml:lang="ru">Liu W., Sun Z., Wei S., Zhang S., Zhu G., Chen L. PS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection // Connection Science. 2024. V. 36. N 1. P. 2295820. https://doi.org/10.1080/09540091.2023.2295820</mixed-citation><mixed-citation xml:lang="en">Liu W., Sun Z., Wei S., Zhang S., Zhu G., Chen L. PS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection // Connection Science. 2024. V. 36. N 1. P. 2295820. https://doi.org/10.1080/09540091.2023.2295820</mixed-citation></citation-alternatives></ref><ref id="cit35"><label>35</label><citation-alternatives><mixed-citation xml:lang="ru">Akber M.A., Ferdousi T., Ahmed R., Asfara R., Rab R., Zakia U. Personality and emotion — a comprehensive analysis using contextual text embeddings // Natural Language Processing Journal. 2024. V. 9. P. 100105. https://doi.org/10.1016/j.nlp.2024.100105</mixed-citation><mixed-citation xml:lang="en">Akber M.A., Ferdousi T., Ahmed R., Asfara R., Rab R., Zakia U. Personality and emotion — a comprehensive analysis using contextual text embeddings // Natural Language Processing Journal. 2024. V. 9. P. 100105. https://doi.org/10.1016/j.nlp.2024.100105</mixed-citation></citation-alternatives></ref><ref id="cit36"><label>36</label><citation-alternatives><mixed-citation xml:lang="ru">Motlagh S.M.H., Rezvani M.H., Khounsiavash M. AI methods for personality traits recognition: a systematic review // Neurocomputing. 2025 . V. 640 . P. 130301. https://doi.org/10.1016/j.neucom.2025.130301</mixed-citation><mixed-citation xml:lang="en">Motlagh S.M.H., Rezvani M.H., Khounsiavash M. AI methods for personality traits recognition: a systematic review // Neurocomputing. 2025 . V. 640 . P. 130301. https://doi.org/10.1016/j.neucom.2025.130301</mixed-citation></citation-alternatives></ref><ref id="cit37"><label>37</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang Y., Yang Q. A Survey on multi-task learning // IEEE Transactions on Knowledge and Data Engineering. 2021. V. 34. N 12. P. 5586–5609. https://doi.org/10.1109/TKDE.2021.3070203</mixed-citation><mixed-citation xml:lang="en">Zhang Y., Yang Q. A Survey on multi-task learning // IEEE Transactions on Knowledge and Data Engineering. 2021. V. 34. N 12. P. 5586–5609. https://doi.org/10.1109/TKDE.2021.3070203</mixed-citation></citation-alternatives></ref><ref id="cit38"><label>38</label><citation-alternatives><mixed-citation xml:lang="ru">Li Y., Kazemeini A., Mehta Y., Cambria E. Multitask learning for emotion and personality traits detection // Neurocomputing. 2022. V. 493. P. 340–350. https://doi.org/10.1016/j.neucom.2022.04.049</mixed-citation><mixed-citation xml:lang="en">Li Y., Kazemeini A., Mehta Y., Cambria E. Multitask learning for emotion and personality traits detection // Neurocomputing. 2022. V. 493. P. 340–350. https://doi.org/10.1016/j.neucom.2022.04.049</mixed-citation></citation-alternatives></ref><ref id="cit39"><label>39</label><citation-alternatives><mixed-citation xml:lang="ru">Talaat F.M., El-Gendy E.M., Saafan M.M., Gamel S.A. Utilizing social media and machine learning for personality and emotion recognition using PERS // Neural Computing and Applications. 2023. V. 35. P. 23927–23941. https://doi.org/10.1007/s00521-023-08962-7</mixed-citation><mixed-citation xml:lang="en">Talaat F.M., El-Gendy E.M., Saafan M.M., Gamel S.A. Utilizing social media and machine learning for personality and emotion recognition using PERS // Neural Computing and Applications. 2023. V. 35. P. 23927–23941. https://doi.org/10.1007/s00521-023-08962-7</mixed-citation></citation-alternatives></ref><ref id="cit40"><label>40</label><citation-alternatives><mixed-citation xml:lang="ru">Sturua S., Mohr I., Akram M.K., Günther M., Wang B., Krimmel M., et al. Jina Embeddings V3: multilingual text encoder with low-rank adaptations // Lecture Notes in Computer Science. 2025. V. 15576. P. 123–129. https://doi.org/10.1007/978-3-031-88720-8_21</mixed-citation><mixed-citation xml:lang="en">Sturua S., Mohr I., Akram M.K., Günther M., Wang B., Krimmel M., et al. Jina Embeddings V3: multilingual text encoder with low-rank adaptations // Lecture Notes in Computer Science. 2025. V. 15576. P. 123–129. https://doi.org/10.1007/978-3-031-88720-8_21</mixed-citation></citation-alternatives></ref><ref id="cit41"><label>41</label><citation-alternatives><mixed-citation xml:lang="ru">Choure A.A., Adhao R.B., Pachghare V.K. NER in Hindi language using transformer model: XLM-RoBERTa // Proc. of the IEEE International Conference on Blockchain and Distributed Systems Security (ICBDS). 2022. P. 1–5. https://doi.org/10.1109/icbds53701.2022.9935841</mixed-citation><mixed-citation xml:lang="en">Choure A.A., Adhao R.B., Pachghare V.K. NER in Hindi language using transformer model: XLM-RoBERTa // Proc. of the IEEE International Conference on Blockchain and Distributed Systems Security (ICBDS). 2022. P. 1–5. https://doi.org/10.1109/icbds53701.2022.9935841</mixed-citation></citation-alternatives></ref><ref id="cit42"><label>42</label><citation-alternatives><mixed-citation xml:lang="ru">Xiao S., Liu Z., Zhang P., Muennighoff N., Lian D., Nie J.-Y. C-Pack: Packed resources for general chinese embeddings // Proc. of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2024. P. 641–649. https://doi.org/10.1145/3626772.3657878</mixed-citation><mixed-citation xml:lang="en">Xiao S., Liu Z., Zhang P., Muennighoff N., Lian D., Nie J.-Y. C-Pack: Packed resources for general chinese embeddings // Proc. of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2024. P. 641–649. https://doi.org/10.1145/3626772.3657878</mixed-citation></citation-alternatives></ref><ref id="cit43"><label>43</label><citation-alternatives><mixed-citation xml:lang="ru">Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., et al. Attention is all you need // Proc. of the 31st Conference on Neural Information Processing Systems. 2017. P. 1–11.</mixed-citation><mixed-citation xml:lang="en">Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., et al. Attention is all you need // Proc. of the 31st Conference on Neural Information Processing Systems. 2017. P. 1–11.</mixed-citation></citation-alternatives></ref><ref id="cit44"><label>44</label><citation-alternatives><mixed-citation xml:lang="ru">Gu A., Dao T. Mamba: linear-time sequence modeling with selective state spaces // arXiv. 2023. arXiv:2312.00752. https://doi.org/10.48550/arXiv.2312.00752</mixed-citation><mixed-citation xml:lang="en">Gu A., Dao T. Mamba: linear-time sequence modeling with selective state spaces // arXiv. 2023. arXiv:2312.00752. https://doi.org/10.48550/arXiv.2312.00752</mixed-citation></citation-alternatives></ref><ref id="cit45"><label>45</label><citation-alternatives><mixed-citation xml:lang="ru">Radford A., Kim J.W., Xu T., Brockman G., McLeavey C., Sutskever I. Robust speech recognition via large-scale weak supervision // Proc. of the 40th International Conference on Machine Learning. 2023. P. 28492–28518.</mixed-citation><mixed-citation xml:lang="en">Radford A., Kim J.W., Xu T., Brockman G., McLeavey C., Sutskever I. Robust speech recognition via large-scale weak supervision // Proc. of the 40th International Conference on Machine Learning. 2023. P. 28492–28518.</mixed-citation></citation-alternatives></ref><ref id="cit46"><label>46</label><citation-alternatives><mixed-citation xml:lang="ru">Demšar J. Statistical comparisons of classifiers over multiple data sets // Journal of Machine Learning Research. 2006. V. 7. P. 1–30.</mixed-citation><mixed-citation xml:lang="en">Demšar J. Statistical comparisons of classifiers over multiple data sets // Journal of Machine Learning Research. 2006. V. 7. P. 1–30.</mixed-citation></citation-alternatives></ref><ref id="cit47"><label>47</label><citation-alternatives><mixed-citation xml:lang="ru">Efron B., Tibshirani R. An Introduction to Bootstrap. Chapman and Hall/CRC, 1994. 456 p.</mixed-citation><mixed-citation xml:lang="en">Efron B., Tibshirani R. An Introduction to Bootstrap. Chapman and Hall/CRC, 1994. 456 p.</mixed-citation></citation-alternatives></ref><ref id="cit48"><label>48</label><citation-alternatives><mixed-citation xml:lang="ru">Selvaraju R.R., Cogswell M., Das A., Vedantam R., Parikh D., Batra D. Grad-CAM: Visual explanations from deep networks via gradient-based localization // Proc. of the IEEE International Conference on Computer Vision (ICCV). 2017. P. 618–626. https://doi.org/10.1109/iccv.2017.74</mixed-citation><mixed-citation xml:lang="en">Selvaraju R.R., Cogswell M., Das A., Vedantam R., Parikh D., Batra D. Grad-CAM: Visual explanations from deep networks via gradient-based localization // Proc. of the IEEE International Conference on Computer Vision (ICCV). 2017. P. 618–626. https://doi.org/10.1109/iccv.2017.74</mixed-citation></citation-alternatives></ref><ref id="cit49"><label>49</label><citation-alternatives><mixed-citation xml:lang="ru">Yang A., Li A., Yang B., Zhang B., Hui B., Zheng B., et al. Qwen3 technical report // arXiv. 2025. arXiv:2505.09388. https://doi.org/10.48550/arXiv.2505.09388</mixed-citation><mixed-citation xml:lang="en">Yang A., Li A., Yang B., Zhang B., Hui B., Zheng B., et al. Qwen3 technical report // arXiv. 2025. arXiv:2505.09388. https://doi.org/10.48550/arXiv.2505.09388</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>
