koz"Вестник Северо-Казахстанского университета имени Манаша Козыбаева"Bulletin of Manash Kozybayev North Kazakhstan University2958-003X2958-0048М. Қозыбаев атындағы СҚУ10.54596/2958-0048-2025-4-195-204koz-2336Research ArticleИНФОРМАЦИОННО-КОММУНИКАЦИОННЫЕ ТЕХНОЛОГИИINFORMATION AND COMMUNICATION TECHNOLOGIESСовременные подходы к классификации фейковых новостейModern approaches for fake news classificationБиляловаА. Б.BilyalovaA. B.

Билялова Айгерим Бериковна.

Алматы

Corresponding author, Master of Social Sciences (2016, L.N. Gumilyov Eurasian National University, Astana), “Kazakh-British Technical University” JSC, School of Information Technologies and Engineering.

Almaty

ai_bilyalova@kbtu.kzКазахстанско-Британский технический университетКазахстанKazakh-British Technical University JSCKazakhstan20251201202604 (68)195204Copyright © Билялова А.Б., 20252025Билялова А.Б.Bilyalova A.B.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.ku.edu.kz/jour/article/view/2336

В данном исследовании рассматривается задача классификации с целью определения, является ли текст подлинным или фейковым. Используются современные архитектуры глубинного обучения в области обработки естественного языка (NLP) модели BERT, ALBERT и GPT-2. С помощью этих передовых моделей исследование направлено на разработку точных и устойчивых методов классификации для эффективного различения фейковых и реальных новостей. Результаты тестирования показали, что предложенные методы имеют потенциал для применения при различении новостей, содержащих ложную информацию, от тех, что отражают действительность.

This study addresses the problem of classification to determine whether a text is authentic or genuine. It uses state-of-the-art deep learning architectures in natural language processing (NLP), the Bert, Albert and GPT-2 models. Using these advanced models, the study aims to develop accurate and robust classification approaches to effectively distinguish between fake and real news. The test result showed that the proposed method has the potential to be used in distinguishing news that does not contain truth from those that do.

Обнаружение фейковых новостейКлассификация текстаОбработка естественного языка (NLP)Глубокое обучениеТрансформерыМашинное обучениеFake News DetectionText ClassificationNatural Language Processing (NLP)Deep LearningTransformer ModelsMachine LearningReferencesSaadi A., Enhancing Fake News Detection with Transformer Models and Summarization // Engineering, Technology & Applied Science Research. - 2025. - Vol.15. - No.3. - P.23253-23259.Saadi A., Enhancing Fake News Detection with Transformer Models and Summarization // Engineering, Technology & Applied Science Research. - 2025. - Vol.15. - No.3. - P.23253-23259.Raza N., Abdulkadir S.J., Abid Y.A., Enhancing fake news detection with transformer-based deep learning: A multidisciplinary approach // Plus One. - 2025. - Vol.20. - No.9.Raza N., Abdulkadir S.J., Abid Y.A., Enhancing fake news detection with transformer-based deep learning: A multidisciplinary approach // Plus One. - 2025. - Vol.20. - No.9.Balmas M. When fake news becomes real: Combined exposure to multiple news sources and political attitudes of inefficacy, alienation, and cynicism // Communication Research. - 2014. - Vol.41. - P.430-454.Balmas M. When fake news becomes real: Combined exposure to multiple news sources and political attitudes of inefficacy, alienation, and cynicism // Communication Research. - 2014. - Vol.41. - P.430-454.Nasir J.A., Khan O.S., Varlamis I. Fake news detection: A hybrid CNN–RNN based deep learning approach // International Journal of Information Management Data Insights. - 2021. - Vol.1.Nasir J.A., Khan O.S., Varlamis I. Fake news detection: A hybrid CNN–RNN based deep learning approach // International Journal of Information Management Data Insights. - 2021. - Vol.1.Xu K., Wang F., Wang H., Yang B. Detecting fake news over online social media via domain reputations and content understanding // Tsinghua Science and Technology. - 2020. - Vol.25. - P.20-27.Xu K., Wang F., Wang H., Yang B. Detecting fake news over online social media via domain reputations and content understanding // Tsinghua Science and Technology. - 2020. - Vol.25. - P.20-27.Ligthart A., Catal C., Tekinerdogan B. Analyzing the effectiveness of semi-supervised learning approaches for opinion spam classification // Applied Soft Computing. - 2021. - Vol.101.Ligthart A., Catal C., Tekinerdogan B. Analyzing the effectiveness of semi-supervised learning approaches for opinion spam classification // Applied Soft Computing. - 2021. - Vol.101.Li J., Lei M. A brief survey for fake news detection via deep learning models // Elsevier. - 2022. - Vol.214. - P.1339-1344.Li J., Lei M. A brief survey for fake news detection via deep learning models // Elsevier. - 2022. - Vol.214. - P.1339-1344.Gupta M., Dennehy D., Parra C.M., Mäntymäki M., Dwivedi Y.K. Fake news believability: The effects of political beliefs and espoused cultural values // Information and Management. - 2022. - Vol.60 - No.103745.Gupta M., Dennehy D., Parra C.M., Mäntymäki M., Dwivedi Y.K. Fake news believability: The effects of political beliefs and espoused cultural values // Information and Management. - 2022. - Vol.60 - No.103745.Goldani M.H., Momtazi S., Safabakhsh R. Detecting fake news with capsule neural networks // Applied Soft Computing. - 2021. - Vol.101. - No.106991.Goldani M.H., Momtazi S., Safabakhsh R. Detecting fake news with capsule neural networks // Applied Soft Computing. - 2021. - Vol.101. - No.106991.Meel P., Vishwakarma D.K. Fake news, rumor, information pollution in social media and web: A contemporary survey of state-of-the-arts, challenges and opportunities // Expert Systems with Applications. - 2020. - Vol.153. - No.112986.Meel P., Vishwakarma D.K. Fake news, rumor, information pollution in social media and web: A contemporary survey of state-of-the-arts, challenges and opportunities // Expert Systems with Applications. - 2020. - Vol.153. - No.112986.Kuntur S., Wróblewska A., Paprzycki M., Ganzha M., Under the Influence: A Survey of Large Language Models in Fake News Detection // IEEE Transactions on Artificial Intelligence. - 2025. - Vol.6. - P.458-476.Kuntur S., Wróblewska A., Paprzycki M., Ganzha M., Under the Influence: A Survey of Large Language Models in Fake News Detection // IEEE Transactions on Artificial Intelligence. - 2025. - Vol.6. - P.458-476.Su J., Cardie C., Nakov P. Adapting Fake News Detection to the Era of Large Language Models // Findings of the Association for Computational Linguistics: NAACL. - 2024. - P.1473-1490.Su J., Cardie C., Nakov P. Adapting Fake News Detection to the Era of Large Language Models // Findings of the Association for Computational Linguistics: NAACL. - 2024. - P.1473-1490.Hu B., Sheng Q., Cao J., Shi Y., Li Y., Wang D., Qi P., Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection // AAAI Technical Track on AI for Social Impact Track. - 2024. - Vol.38. - No.20.Hu B., Sheng Q., Cao J., Shi Y., Li Y., Wang D., Qi P., Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection // AAAI Technical Track on AI for Social Impact Track. - 2024. - Vol.38. - No.20.Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding // North American Chapter of the Association for Computational Linguistics. - 2019. - Vol.45.Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding // North American Chapter of the Association for Computational Linguistics. - 2019. - Vol.45.Sanh V., Debut L., Chaumond J., Wolf T. DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter // Computation and Language [Electronic resource]. - 2019. - Available at: https://arxiv.org/abs/1910.01108 (accessed 19.11.2025).Sanh V., Debut L., Chaumond J., Wolf T. DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter // Computation and Language [Electronic resource]. - 2019. - Available at: https://arxiv.org/abs/1910.01108 (accessed 19.11.2025).Liu Y., Ott M., Goyal N., Du J., Joshi M., Chen D., Levy O., Lewis M., Zettlemoyer L., Stoyanov V. RoBERTa: A robustly optimized BERT pretraining approach // Computation and Language. [Electronic resource]. - 2019. - Available at: https://arxiv.org/abs/1907.11692 (accessed 19.11.2025)Liu Y., Ott M., Goyal N., Du J., Joshi M., Chen D., Levy O., Lewis M., Zettlemoyer L., Stoyanov V. RoBERTa: A robustly optimized BERT pretraining approach // Computation and Language. [Electronic resource]. - 2019. - Available at: https://arxiv.org/abs/1907.11692 (accessed 19.11.2025)

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