infojournalИнформатика и образованиеInformatics and education0234-04532658-7769Publishing House Education and Informatics10.32517/0234-0453-2024-39-6-82-96infojournal-1158Research ArticleИНФОРМАТИЗАЦИЯ ОБРАЗОВАНИЯINFORMATIZATION OF EDUCATIONПрименение больших языковых моделей для формирования навыков анализа медиаконтекста в обучении студентов филологических специальностейUsing large language models to develop skills in analyzing media context in students of philological specialtieshttps://orcid.org/0009-0002-5829-2379ИвэньГ.YiwenG.

Ивэнь Гао, аспирант кафедры зарубежной журналистики илитературы, факультет журналистики

г. Москва

Gao Yiwen, a postgraduate student at the Department ofForeign Journalism and Literature, Faculty of Journalism

Moscow

qin.chi@yandex.ruМосковский государственный университет имени М. В. ЛомоносоваРоссияLomonosov Moscow State UniversityRussian Federation2024250220253968296Copyright © Ивэнь Г., 20252025Ивэнь Г.Yiwen G.This work is licensed under a Creative Commons Attribution 4.0 License.https://info.infojournal.ru/jour/article/view/1158

В современных условиях цифровизации образования, в том числе гуманитарного, особую актуальность и практическую значимость для совершенствования профессиональной подготовки студентов филологических специальностей приобретает использование технологий обработки естественного языка и больших языковых моделей (англ. Large Language Model, LLM). В статье исследуются возможности применения LLM для объективного анализа медиаконтекста в обучении студентов-филологов. На основе критического анализа литературы и эмпирического исследования с использованием методов тематического моделирования, анализа тональности и извлечения фактов на материале корпуса текстов СМИ объемом 5,2 млн единиц выявлены ключевые тематические и языковые особенности медиаконтекста, значимые для развития профессиональных компетенций филологов. Разработана концептуальная модель интеграции методов LLM в адаптивные обучающие системы для персонализированного формирования навыков анализа медиаконтекста. Экспериментальная апробация модели на выборке из 120 студентов продемонстрировала статистически значимое повышение результатов обучения и удовлетворенности обучающихся по сравнению с контрольной группой. Полученные результаты открывают перспективы для создания интеллектуальных адаптивных систем подготовки филологов к работе в условиях трансформации медиаландшафта. 

Under modern conditions of digitalization of education, including liberal arts education, the use of natural language processing technologies and large language models (LLM) is of particular relevance and practical significance for improving professional training of students of philological specialties. The article explores the possibilities of using LLM for objective analysis of media context in the training of philology students. On the basis of critical analysis of literature and empirical research using the methods of thematic modeling, tonality analysis and fact extraction on the material of a corpus of 5,2 million media texts, the key thematic and linguistic features of the media context significant for the development of professional competencies of philology students are revealed. A conceptual model of integrating LLM methods into adaptive learning systems for personalized formation of media context analysis skills was developed. Experimental testing of the model on a sample of 120 students demonstrated a statistically significant increase in learning outcomes and learner satisfaction compared to the control group. The obtained results open prospects for the creation of intelligent adaptive systems for training philologists to work in a transforming media landscape. 

большие языковые моделимедиаконтекстфилологическое образованиеанализ текстов СМИадаптивное обучениецифровые компетенцииlarge language modelsLLMmedia contextphilological educationmedia text analysisadaptive learningdigital competenciesReferencesBlei D. M., Ng A. Y., Jordan M. I. Latent Dirichlet allocation. Journal of Machine Learning Research. 2003;3:993–1022.Blei D. M., Ng A. Y., Jordan M. I. Latent Dirichlet allocation. Journal of Machine Learning Research. 2003;3:993–1022.Diakopoulos N. Automating the news: How algorithms are rewriting the media. Cambridge, Massachusetts, USA, Harvard University Press; 2019. 336 p.Diakopoulos N. Automating the news: How algorithms are rewriting the media. Cambridge, Massachusetts, USA, Harvard University Press; 2019. 336 p.Iliev R., Dehghani M., Sagi E. Automated text analysis in psychology: Methods, applications, and future developments. Language and Cognition. 2015;7(2):265–290. DOI: 10.1017/langcog.2014.30.Iliev R., DehghaniM., Sagi E. Automated text analysis in psychology: Methods, applications, and future developments. Language and Cognition. 2015;7(2):265–290. DOI: 10.1017/langcog.2014.30.Mikolov T., Sutskever I., Chen K., Corrado G., Dean J. Distributed representations of words and phrases and their compositionality. Proc. 26th Int. Conf. on Neural Information Processing Systems (NIPS’13). Red Hook, NY, USA, Curran Associates Inc.; 2013;2:3111–3119. DOI: 10.48550/arXiv.1310.4546.Mikolov T., Sutskever I., Chen K., Corrado G., Dean J. Distributed representations of words and phrases and their compositionality. Proc. 26th Int. Conf. on Neural Information Processing Systems (NIPS’13). Red Hook, NY, USA, Curran Associates Inc.; 2013;2:3111–3119. DOI: 10.48550/arXiv.1310.4546.Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint. 2019:1–16. DOI: 10.48550/arXiv.1810.04805.Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint. 2019:1–16. DOI: 10.48550/arXiv.1810.04805.Guo L., Vargo C., Pan Z., Ding W., Ishwar P. Big social data analytics in journalism and mass communication. Journalism & Mass Communication Quarterly. 2016;93(2):332– 359. DOI: 10.1177/1077699016639231.Guo L., Vargo C., Pan Z., Ding W., Ishwar P. Big social data analytics in journalism and mass communication. Journalism & Mass Communication Quarterly. 2016;93(2):332– 359. DOI: 10.1177/1077699016639231.Leskovec J., Backstrom L., Kleinberg J. Meme-tracking and the dynamics of the news cycle. Proc. 15th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD’09). New York, NY, USA, Association for Computing Machinery; 2009:497–506. DOI: 10.1145/1557019.1557077.Leskovec J., Backstrom L., KleinbergJ. Meme-tracking and the dynamics of the news cycle. Proc. 15th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD’09). New York, NY, USA, Association for Computing Machinery; 2009:497–506. DOI: 10.1145/1557019.1557077.Pariser E. The filter bubble: What the Internet is hiding from you. USA, Penguin Press; 2011. 304 p.Pariser E. The filter bubble: What the Internet is hiding from you. USA, Penguin Press; 2011. 304 p.Radford A., Wu J., Child R., Luan D., Amodei D., Sutskever I. Language models are unsupervised multitask learners. OpenAI. 2019;1(8):1–24.Radford A., Wu J., Child R., Luan D., Amodei D., Sutskever I. Language models are unsupervised multitask learners. OpenAI. 2019;1(8):1–24.Vargo C. J., Guo L., Amazeen M. A. The agendasetting power of fake news: A big data analysis of the online media landscape from 2014 to 2016. New Media & Society. 2017;20(5):2028–2049. DOI: 10.1177/1461444817712086.Vargo C. J., Guo L., Amazeen M. A. The agendasetting power of fake news: A big data analysis of the online media landscape from 2014 to 2016. New Media & Society. 2017;20(5):2028–2049. DOI: 10.1177/1461444817712086.Zhao W. X., Jiang J., He J., Song Y., Achanauparp P., Lim E.-P., Li X. Topical keyphrase extraction from twitter. Proc. 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Portland, Oregon, USA, Association for Computational Linguistics; 2011;1:379–388.ZhaoW. X., Jiang J., He J., Song Y., Achanauparp P., Lim E.-P., Li X. Topical keyphrase extraction from twitter. Proc. 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Portland, Oregon, USA, Association for Computational Linguistics; 2011;1:379–388.Дудихин В. В., Кондрашов П. Е. Методология использования больших языковых моделей для решения задач государственного и муниципального управления по интеллектуальному реферированию иавтоматическому формированию текстового контента. Государственное управление. Электронный вестник. 2024;(105):169–179. EDN: JBMLWE. DOI: 10.55959/MSU2070-1381-105-2024-169-179.Dudikhin V. V., Kondrashov P. E. Methodology of using large language models to solve tasks of state and municipal government for intelligent abstracting and automatic generation of text content. E-journal Public Administration. 2024;(105):169–179. (In Russian.) EDN: JBMLWE. DOI: 10.55959/MSU2070-1381-105-2024-169-179.]Abeysiriwardana P. C., Jayasinghe-Mudalige U. K., Kodituwakku S. R. “Connected researches” in “smart lab bubble”: A lifeline of techno-society space for commercial agriculture development in “new normal”. New Techno Humanities. 2022;2(1):79–91. DOI: 10.1016/j.techum.2022.05.001.Abeysiriwardana P. C., Jayasinghe-Mudalige U. K., Kodituwakku S. R. “Connected researches” in “smart lab bubble”: A lifeline of techno-society space for commercial agriculture development in “new normal”. New Techno Humanities. 2022;2(1):79–91. DOI: 10.1016/j.techum.2022.05.001.Khan A. F., Chiarcos Ch., Declerck T., Gifu D., García E. G.-B., Gracia J., Ionov M., Labropoulou P., Mambrini F., McCrae J., Pagé-Perron É., Passarotti M., Ros S., Truică C.-O. When linguistics meets web technologies: Recent advances in modelling linguistic linked data. Semantic Web. 2022;13(6):1–64. DOI: 10.3233/SW-222859.Khan A. F., Chiarcos Ch., Declerck T., Gifu D., García E. G.-B., Gracia J., Ionov M., Labropoulou P., Mambrini F., McCrae J., Pagé-Perron É., Passarotti M., Ros S., Truică C.-O. When linguistics meets web technologies: Recent advances in modelling linguistic linked data. Semantic Web. 2022;13(6):1–64. DOI: 10.3233/SW-222859.Katerynych P., Goian V., Goian O. Exploring the evolution of storytelling in the streaming era: A study of narrative trends in Netflix original content. Communication Today. 2023;14(2):3–12. DOI: 10.34135/communicationtoday.2023.Vol.14.No.2.3.Katerynych P., GoianV., GoianO. Exploring the evolution of storytelling in the streaming era: A study of narrative trends in Netflix original content. Communication Today. 2023;14(2):3–12. DOI: 10.34135/communicationtoday.2023.Vol.14.No.2.3.Naveed H., Khan A. U., Qiu S., Saqib M., Anwar S., Usman M., Akhtar N., Barnes N., Mian A. Comprehensive overview of large language models. arXiv preprint. 2023:1– 47. DOI: 10.48550/arXiv.2307.06435.Naveed H., Khan A. U., Qiu S., Saqib M., Anwar S., Usman M., Akhtar N., Barnes N., Mian A. Comprehensive overview of large language models. arXiv preprint. 2023:1– 47. DOI: 10.48550/arXiv.2307.06435.Movva R., Balachandar S., Peng K., Agostini G., Garg N., Pierson E. Topics, authors, and institutions in large language model research: Trends from 17K arXiv Papers. arXiv preprint. 2023:1–21. DOI: 10.48550/arXiv.2307.10700.Movva R., Balachandar S., Peng K., Agostini G., Garg N., Pierson E. Topics, authors, and institutions in large language model research: Trends from 17K arXiv Papers. arXiv preprint. 2023:1–21. DOI: 10.48550/arXiv.2307.10700.Carroll J. B. A model of school learning. Teachers College Record. 1963;64(8):723–733. DOI: 10.1177/016146816306400801.Carroll J. B. A model of school learning. Teachers College Record. 1963;64(8):723–733. DOI: 10.1177/016146816306400801.Brown T. B., Mann B., Ryder N., Subbiah M., Kaplan J. D., Dhariwal P., Neelakantan A., Shyam P., Sastry G., Askell A., Agarwal S., Herbert-Voss A., Krueger G., Henighan T., Child R., Ramesh A., Ziegler D. M., Wu J., Winter C., Hesse Ch., Chen M., Sigler E., Litwin M., Gray S., Chess B., Clark J., Berner Ch., McCandlish S., Radford A., Sutskever I., Amodei D. Language models are few-shot learners. arXiv preprint. 2020:1–75. DOI: 10.48550/arXiv.2005.14165.Brown T. B., Mann B., Ryder N., Subbiah M., Kaplan J. D., Dhariwal P., Neelakantan A., Shyam P., Sastry G., Askell A., Agarwal S., Herbert-Voss A., Krueger G., Henighan T., Child R., Ramesh A., Ziegler D. M., Wu J., Winter C., Hesse Ch., Chen M., Sigler E., Litwin M., Gray S., Chess B., Clark J., Berner Ch., McCandlish S., Radford A., Sutskever I., Amodei D. Language models are few-shot learners. arXiv preprint. 2020:1–75. DOI: 10.48550/arXiv.2005.14165.Radford A., Kim J. W., Hallacy C., Ramesh A., Goh G., Agarwal S., Sastry G., Askell A., Mishkin P., Clark J., Krueger G., Sutskever I. Learning transferable visual models from natural language supervision. arXiv preprint. 2021:1– 48. DOI: 10.48550/arXiv.2103.00020.Radford A., Kim J. W., Hallacy C., Ramesh A., Goh G., Agarwal S., Sastry G., Askell A., Mishkin P., Clark J., Krueger G., Sutskever I. Learning transferable visual models from natural language supervision. arXiv preprint. 2021:1– 48. DOI: 10.48550/arXiv.2103.00020.Bommasani R., Hudson D. A., Adeli E., Altman R., Arora S., Von Arx S., Bernstein M. S., Bohg J., Bosselut A., Brunskill E., Brynjolfsson E., Buch S., Card D., Castellon R., Chatterji N., Chen A., Creel K., Davis J. Q., Demszky D., Donahue C., Doumbouya M., Durmus E., Ermon S., Etchemendy J., Ethayarajh K., Fei-Fei L., Finn Ch., Gale T., Gillespie L., Goel K., Goodman N., Grossman S., Guha N., Hashimoto T., Henderson P., Hewitt J., Ho D. E., Hong J., Hsu K., Huang J., Icard T., Jain S., Jurafsky D., Kalluri P., Karamcheti S., Keeling G., Khani F., Khattab O., Koh P. W., Krass M., Krishna R., Kuditipudi R., Kumar A., Ladhak F., Lee M., Lee T., Leskovec J., Levent I., Li X. L., Li X., Ma T., Malik A., Manning C. D., Mirchandani S., Mitchell E., Munyikwa Z., Nair S., Narayan A., Narayanan D., Newman B., Nie A., Niebles J. C., Nilforoshan H., Nyarko J., Ogut G., Orr L., Papadimitriou I., Park J. S., Piech C., Portelance E., Potts C., Raghunathan A., Reich R., Ren H., Rong F., Roohani Y., Ruiz C., Ryan J., Ré C., Sadigh D., Sagawa S., Santhanam K., Shih A., Srinivasan K., Tamkin A., Taori R., Thomas A. W., Tramèr F., Wang R. E., Wang W., Wu B., Wu J., Wu Y., Xie S. M., Yasunaga M., You J., Zaharia M., Zhang M., Zhang T., Zhang X., Zhang Y., Zheng L., Zhou K., Liang P. On the opportunities and risks of foundation models. arXiv preprint. 2021:1–214. DOI: 10.48550/arXiv.2108.07258.Bommasani R., Hudson D. A., Adeli E., Altman R., Arora S., Von Arx S., Bernstein M. S., Bohg J., Bosselut A., Brunskill E., Brynjolfsson E., Buch S., Card D., Castellon R., Chatterji N., Chen A., Creel K., Davis J. Q., Demszky D., Donahue C., DoumbouyaM., Durmus E., Ermon S., Etchemendy J., Ethayarajh K., Fei-Fei L., Finn Ch., Gale T., Gillespie L., Goel K., Goodman N., Grossman S., Guha N., Hashimoto T., Henderson P., Hewitt J., Ho D. E., Hong J., Hsu K., Huang J., Icard T., Jain S., Jurafsky D., Kalluri P., Karamcheti S., Keeling G., Khani F., Khattab O., Koh P. W., Krass M., Krishna R., Kuditipudi R., Kumar A., Ladhak F., Lee M., Lee T., Leskovec J., Levent I., Li X. L., Li X., Ma T., Malik A., ManningC. D., MirchandaniS., Mitchell E., Munyikwa Z., NairS., Narayan A., Narayanan D., Newman B., Nie A., Niebles J. C., Nilforoshan H., Nyarko J., Ogut G., Orr L., Papadimitriou I., Park J. S., Piech C., Portelance E., Potts C., Raghunathan A., Reich R., Ren H., Rong F., Roohani Y., Ruiz C., Ryan J., Ré C., Sadigh D., Sagawa S., Santhanam K., Shih A., Srinivasan K., Tamkin A., Taori R., Thomas A. W., Tramèr F., Wang R. E., Wang W., Wu B., Wu J., Wu Y., Xie S. M., Yasunaga M., You J., Zaharia M., Zhang M., Zhang T., Zhang X., Zhang Y., Zheng L., Zhou K., Liang P. On the opportunities and risks of foundation models. arXiv preprint. 2021:1–214. DOI: 10.48550/arXiv.2108.07258.Fiedler S. H. D., Väljataga T. Personal learning environments: Concept or technology? International Journal of Virtual and Personal Learning Environments. 2011;2(4):1– 11. DOI: 10.4018/jvple.2011100101.Fiedler S. H. D., Väljataga T. Personal learning environments: Concept or technology? International Journal of Virtual and Personal Learning Environments. 2011;2(4):1– 11. DOI: 10.4018/jvple.2011100101.

The authors declare that there are no conflicts of interest present.