https://doi.org/10.62660/bcstu/4.2025.82

Volume 30, No. 4, 2025

82-96

  • Read article

    • AI-based model of a researcher support service

    Maksym Shovkoplias

    Received 22.06.2025, Revised 08.11.2025, Accepted 15.12.2025

    Abstract

    Between 2020 and 2025, researchers faced challenges such as fragmented digital platforms, information overload, and limited personalisation capabilities. This underscored the need for services capable of providing comprehensive support for research activities. The aim of this study was to develop a conceptual model of an intelligent information service focused on personalised researcher support. The proposed system architecture was built using structural modelling, functional analysis, machine learning, and natural language processing techniques. It includes modules for recommendations, virtual collaboration, event management, and automated bibliography generation. A multi-layered user model was designed, taking into account scientific interests, interaction history, and research context. The combination of semantic analysis with behavioural patterns increased recommendation relevance by 20-30%. The prototype of the system was tested in March 2025 with the participation of 15 young scientists from three Ukrainian universities. The results of the survey and practical tasks showed that the average time spent searching for relevant literature was reduced by 35%, task planning efficiency increased by 40%, and user satisfaction with the service's functionality reached 87%. Respondents highly rated the convenience of the interface (4.5 out of 5), the relevance of recommendations (4.3), and co-authoring tools (4.6). Three new academic collaborations were initiated through the co-author selection module. The data obtained confirmed the effectiveness of the model in increasing research productivity, improving collaboration, and providing personalised user support. The proposed structure allows for scaling to different disciplines and has the potential to be implemented in digital platforms focused on scientific activity

    Keywords:

    scientific information personalisation; semantic analysis; adaptive recommendations; machine learning; intelligent systems; digital research environment

    Suggested citation
    Shovkoplias, M. (2025). AI-based model of a researcher support service. Bulletin of Cherkasy State Technological University, 30(4), 82-96. https://doi.org/10.62660/bcstu/4.2025.82
    412 Views

    References

    1. Adewale, T. (2022). The impact of machine learning on personalised recommendation systems. Retrieved from https://www.researchgate.net/publication/386337230.
    2. Akinnagbe, O.B. (2024). The future of artificial intelligence: Trends and predictions. Mikailalsys Journal of Advanced Engineering International, 1(3), 249-261. doi: 10.58578/mjaei.v1i3.4125
    3. Declaration of Helsinki. (2024). Retrieved from https://www.wma.net/what-we-do/medical-ethics/declarationof-helsinki.
    4. Ko, H., Lee, S., Park, Y., & Choi, A. (2022). A survey of recommendation systems: Recommendation models, techniques, and application fields. Electronics, 11(1), article number 141. doi: 10.3390/electronics11010141.
    5. Koval, Y. (2022). Application of modern information systems and technologies in scientific activity. Pedagogy and Education Management Review (PEMR), 5(7), 11-18. doi: 10.36690/2733-2039-2022-5-11.
    6. Kreutz, C.K., & Schenkel, R. (2022). Scientific paper recommendation systems: A literature review of recent publications. International Journal on Digital Libraries, 23, 149-165. doi: 10.1007/s00799-022-00339-w.
    7. Lemon, K.N., & Verhoef, P.C. (2016). Understanding customer experience throughout the customer journey. Journal of Marketing, 80(6), 69-96. doi: 10.1509/jm.15.0420.
    8. Li, Y., Liu, K., Satapathy, R., Wang, S., & Cambria, E. (2023). Recent developments in recommender systems: A survey. ArXiv. doi: 10.48550/arXiv.2306.12680.
    9. Masciari, E., Umair, A., & Habib Ullah, M.A. (2024). A systematic literature review on AI-based recommendation systems and their ethical considerations. IEEE Access, 12, 22445-22463. doi: 10.1109/ACCESS.2024.3451054.
    10. Nikiforova, L., Dohtieva, I., & Zharinov, S. (2025). Specificity of the design of the development of an information resource and an electronic register of scientific professional publications in the context of digitalization of the scientific field. Innovation and Sustainability, 4, 62-75. doi: 10.31649/ins.2024.4.62.75.
    11. Petryna, D., Kornuta, V., & Kornuta, O. (2024). Using neural network tools to accelerate the development of Web interfaces. Information Technologies and Computer Engineering, 21(2), 42-50. doi: 10.31649/1999-9941-202460-2-42-50.
    12. Putri, C.A., Syaifuddin, A., Rohman, N., Aziz, A., & Ponijan, R.M.P. (2025). Optimizing the use of digital libraries in basic education. Edunesia: Jurnal Ilmiah Pendidikan, 6(1), 1-13. doi: 10.51276/edu.v6i1.940.
    13. Roy, D., & Dutta, M. (2022). A systematic review and research perspective on recommender systems. Journal of Big Data, 9, article number 59. doi: 10.1186/s40537-022-00592-5.
    14. Sangeetha, N., Thangaraj, H., Vashisht, V., Joshi, E., Verma, K., & Katariya, D. (2025). A BERT based hybrid recommendation system for academic collaboration. ArXiv. doi: 10.48550/arXiv.2502.15223.
    15. Shovkoplias, M.O., & Liubchak, V.O. (2024). Review of models and methods for individual customization of a scientist’s information service. Information Technology: Computer Science, Software Engineering and Cyber Security, 5, 47-56. doi: 10.32782/IT/2024-2-11.
    16. Umbach, G. (2024). Open science and the impact of open access, open data, and FAIR publishing principles on data-driven academic research: Towards ever more transparent, accessible, and reproducible academic output? Statistical Journal of the IAOS, 40(1), 59-70. doi: 10.3233/SJI-240021.
    17. Vargo, S.L., & Lusch, R.F. (2025). Service-dominant logic 2025. International Journal of Research in Marketing, 34(1), 46-67. doi: 10.1016/j.ijresmar.2016.11.001.
    18. Wilson, A., Zeithaml, V.A., Bitner, M. J., & Gremler, D.D. (2016). Services marketing: Integrating customer focus across the firm (3rd ed.). New York: McGraw Hill.
    19. Wirtz, J., & Lovelock, C. (2021). Services marketing: People, technology, strategy (9th ed.). Singapore: World Scientific. doi: 10.1142/y0024.
    20. Yu, F., Ruel, L., Tyler, R., & Xu, Q. (2020). Innovative UX methods for information access based on interdisciplinary approaches: Practical lessons from academia and industry. Data and Information Management, 4(1), 74-80. doi: 10.2478/dim-2020-0004.