Application of Natural Language Processing for Adaptive Navigation in Recommender Systems
DOI:
https://doi.org/10.24160/1993-6982-2025-3-118-125Keywords:
natural language processing, adaptive navigation, recommender systems, ext analysis, transformer modelsAbstract
The purpose of the study is to explore the application of natural language processing (NLP) methods for developing adaptive navigation in recommender systems. This will help improve personalization and interaction with the user in real-time environments. The system architecture is proposed, which utilizes modern NLP frameworks such as Hugging Face, TensorFlow, and PyTorch. The study methodology is based on the integration of NLP techniques for analysis of text data, prediction of user intentions, and dynamic adaptation of interfaces. Transformer models, such as BERT and GPT, were employed, due to which better accuracy of query analysis and personalization of recommendations was achieved.
The study results have demonstrated that the use of NLP in recommender systems allows significantly better quality of the proposals to be obtained. Adaptive navigation based on analyzing texts and predicting user intentions opens the possibility to dynamically modify the user interface, thereby enhancing the user experience and improving the relevance of recommendations. The study results can be used in such digital platforms as internet shops, streaming services, and electronic learning platforms.
The study emphasizes the importance of using NLP to create personalized interfaces. The application of transformer models for real-time prediction of user intentions improves the quality of interaction with the user, thereby making recommender systems more flexible and adaptive to the changing needs of users.
References
2. Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding // Proc. NAACL-HLT. 2019. Pp. 4171—4186.
3. Brown T. e. a. Language Models are Few-shot Learners // Advances in Neural Information Proc. Systems. 2020. V. 33. Pp. 1877—1901.
4. Covington P., Adams J., Sargin E. Deep Neural Networks for YouTube Recommendations // Proc. X ACM Conf. Recommender Systems. 2016. Pp. 191—198.
5. Madhurika B., Malleswari Naga D. Deep Learning-based Hybrid Recommendation System with NLP — HAEK-based Sentiment Analysis // Intern. J. Intelligent Systems and Appl. in Eng. 2024. V. 12(3). Pp. 2438—2449.
6. Гомзин А.Г., Коршунов А.В. Системы рекомендаций: обзор современных подходов // Труды Института системного программирования РАН. 2012. Т. 22. С. 401—418.
7. Kaouni M. e. a. Integrating Artificial Intelligence and Natural Language Processing in E-learning Platforms: a Review of Opportunities and Limitations // Proc. VII IEEE Congress Information Sci. & Technol. Agadir, 2023.
8. Лейн Х., Хапке Х., Ховард К. Обработка естественного языка в действии. СПб.: Питер, 2020.
9. Qian Zhang, Jie Lu. Artificial Intelligence in Recommender Systems // Complex Intel. Syst. 2021. V. 7. Pp. 439—457.
10. Zheyu Wang e. a. Using Natural Language Processing Techniques to Provide Personalized Educational Materials for Chronic Disease Patients in China: Development and Assessment of a Knowledge-based Health Recommender System // JMIR Med. Inform. 2020. V. 23. No. 8(4). P. e17642.
11. Jurafsky D., Martin J.H. Speech and Language Processing. New Jersey: Prentice-Hall Inc., 2021.
12. Волков С.И. Методы и алгоритмы машинного обучения. М.: Наука, 2016.
---
Для цитирования: Рудак Л.В., Зори С.А. Применение обработки естественного языка для адаптивной навигации в системах рекомендаций // Вестник МЭИ. 2025. № 3. С. 118—125. DOI: 10.24160/1993-6982-2025-3-118-125
---
Конфликт интересов: авторы заявляют об отсутствии конфликта интересов
#
1. Morozov A.A. Vvedenie v Obrabotku Estestvennogo Yazyka. M.: Nauka, 2018. (in Russian).
2. Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proc. NAACL-HLT. 2019:4171—4186.
3. Brown T. e. a. Language Models are Few-shot Learners. Advances in Neural Information Proc. Systems. 2020;33:1877—1901.
4. Covington P., Adams J., Sargin E. Deep Neural Networks for YouTube Recommendations. Proc. X ACM Conf. Recommender Systems. 2016:191—198.
5. Madhurika B., Malleswari Naga D. Deep Learning-based Hybrid Recommendation System with NLP — HAEK-based Sentiment Analysis. Intern. J. Intelligent Systems and Appl. in Eng. 2024;12(3):2438—2449.
6. Gomzin A.G., Korshunov A.V. Sistemy Rekomendatsiy: Obzor Sovremennykh Podkhodov. Trudy Instituta Sistemnogo Programmirovaniya RAN. 2012;22:401—418. (in Russian).
7. Kaouni M. e. a. Integrating Artificial Intelligence and Natural Language Processing in E-learning Platforms: a Review of Opportunities and Limitations. Proc. VII IEEE Congress Information Sci. & Technol. Agadir, 2023.
8. Leyn Kh., Khapke Kh., Khovard K. Obrabotka Estestvennogo Yazyka v Deystvii. SPb.: Piter, 2020. (in Russian).
9. Qian Zhang, Jie Lu. Artificial Intelligence in Recommender Systems. Complex Intel. Syst. 2021;7:439—457.
10. Zheyu Wang e. a. Using Natural Language Processing Techniques to Provide Personalized Educational Materials for Chronic Disease Patients in China: Development and Assessment of a Knowledge-based Health Recommender System. JMIR Med. Inform. 2020;23;8(4):e17642.
11. Jurafsky D., Martin J.H. Speech and Language Processing. New Jersey: Prentice-Hall Inc., 2021.
12. Volkov S.I. Metody i Algoritmy Mashinnogo Obucheniya. M.: Nauka, 2016. (in Russian)
---
For citation: Rudak L.V., Zori S.A. Application of Natural Language Processing for Adaptive Navigation in Recommender Systems. Bulletin of MPEI. 2025;3:118—125. (in Russian). DOI: 10.24160/1993-6982-2025-3-118-125
---
Conflict of interests: the authors declare no conflict of interest
