A Multimodal Artificial Intelligence Assistant for Optimizing Admissions Communication at UNAMBA
Article Sidebar
Main Article Content
Abstract
Generative Artificial Intelligence is transforming communication processes in higher education through conversational assistants capable of automating institutional support. This study aimed to implement a multimodal Artificial Intelligence assistant to optimize communication with applicants at the Universidad Nacional Micaela Bastidas de Apurímac. The methodology followed a quantitative and applied approach, integrating operational performance analysis, content validation, and user satisfaction assessment. During a 230-day operational period, the assistant handled 1,839 queries from 348 users, achieving an automatic response rate of 92.99 % and response times of less than one minute. The generated content was validated by experts, obtaining a global Aiken's V coefficient of 0.889, while the EUCS instrument demonstrated excellent reliability (Cronbach's α = 0.966), reflecting high levels of applicant satisfaction. It is concluded that AI-based multimodal assistants were associated with high levels of applicant satisfaction and constitute an alternative for enhancing information accessibility and communication efficiency, contributing to digital transformation in public universities.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
When an author creates an article and publishes it in a journal, the copyright passes to the journal as part of the publishing agreement. Therefore, the journal becomes the owner of the rights to reproduce, distribute and sell the article. The author retains some rights, such as the right to be recognized as the creator of the article and the right to use the article for his or her own scholarly or research purposes, unless otherwise agreed in the publication agreement.
How to Cite
References
[1] A. Vaswani et al., “Attention Is All You Need,” in Advances in Neural Information Processing Sys-tems, vol. 30, Red Hook, NY, USA: Curran Associa-tes, Inc., 2017, pp. 5998–6008.
[2] OpenAI, “GPT-4 Technical Report,” arXiv preprint arXiv:2303.08774, 2023, doi: 10.48550/arXiv.2303.08774.
[3] T. B. Brown et al., “Language Models are Few-Shot Learners,” in Advances in Neural Information Pro-cessing Systems, vol. 33, 2020, pp. 1877–1901.
[4] M. S. Stepanov, V. G. Popov, N. K. Fedorova, F. S. Kroshin, and A. R. Muzata, “The Automation of Client Servicing in University and College Admis-sion Office,” in 2023 Systems of Signals Generating and Processing in the Field of on Board Communica-tions, Moscow, Russia, 2023, pp. 1–7, doi: 10.1109/IEEECONF56737.2023.10092103.
[5] S. Hu, F. Ke, D. Vyortkina, P. Hu, S. Luby, and J. O’Shea, “Artificial intelligence in higher education: Applications, challenges, policy development, and additional considerations,” in Higher Education: Handbook of Theory and Research, vol. 40, L. W. Perna, Ed. Cham, Switzerland: Springer, 2025, pp. 1–39, doi: 10.1007/978-3-031-51930-7_13-1.
[6] Instituto Nacional de Estadística e Informática (INEI), Estadísticas de las Tecnologías de Informa-ción y Comunicación en los Hogares. Lima, Perú: INEI, 2024.
[7] N. A. Al-Madi, K. Abu Maria, M. A. Al-Madi, M. A. Alia, and E. Abu Maria, “An intelligent Arabic chat-bot system proposed framework,” in 2021 Interna-tional Conference on Information Technology (ICIT), Amman, Jordan, Jul. 2021, pp. 1–6, doi: 10.1109/ICIT52682.2021.9491699.
[8] M. R. A. Prasetya and A. M. Priyatno, “Dice simila-rity and TF-IDF for new student admissions chat-bot,” Journal of Artificial Intelligence and Digital Business (RIGGS), vol. 1, no. 1, pp. 1–8, 2022, doi: 10.31004/riggs.v1i1.5.
[9] S. W. Taju, G. F. Mandias, J. H. Moedjahedy, A. K. Wahyudi, R. Rotikan, and E. Y. Putra, “AI-powered chatbot for information service at Klabat University by integrating OpenAI GPT-3 with intent recogni-tion and semantic search,” in 2023 5th International Conference on Cybernetics and Intelligent System (ICORIS), Pangkalpinang, Indonesia, Oct. 2023, pp. 1–6, doi: 10.1109/ICORIS60118.2023.10352259.
[10] A. Aloqayli and H. Abdelhafez, “Intelligent chatbot for admission in higher education,” International Journal of Information and Education Technology, vol. 13, no. 9, pp. 1348–1357, Sep. 2023, doi: 10.18178/ijiet.2023.13.9.1937.
[11] H. Vega-Huerta, F. Gutierrez-Mejía, B. Calcina-Aguilar, O. Benito-Pacheco, P. De-la-Cruz-VdV, G. L. E. Maquen-Niño, and J. C. Lázaro-Guillermo, “ChatGPT-based conversational artificial intelligen-ce system for virtual university admissions office client attention,” Ingénierie des Systèmes d’Information, vol. 30, no. 4, pp. 945–952, 2025, doi: 10.18280/isi.300411.
[12] E. Kasneci et al., “ChatGPT for good? On opportuni-ties and challenges of large language models for education,” Learning and Individual Differences, vol. 103, p. 102274, 2023, doi: 10.1016/j.lindif.2023.102274.
[13] D. Zawacki-Richter, V. I. Marín, M. Bond, and F. Gouverneur, “Systematic review of research on arti-ficial intelligence applications in higher education,” International Journal of Educational Technology in Higher Education, vol. 16, no. 39, 2019, doi: 10.1186/s41239-019-0171-0.
[14] O. Okonkwo and S. Ade-Ibijola, “Chatbots applica-tions in education: A systematic review,” Compu-ters and Education: Artificial Intelligence, vol. 2, p. 100033, 2021, doi: 10.1016/j.caeai.2021.100033.
[15] J. W. Creswell and J. D. Creswell, Research Design: Qualitative, Quantitative, and Mixed Methods Ap-proaches, 5th ed. Thousand Oaks, CA, USA: Sage, 2018.
[16] R. Hernández-Sampieri and C. Mendoza, Metodolo-gía de la investigación: Las rutas cuantitativa, cuali-tativa y mixta. Ciudad de México, México: McGraw-Hill, 2018.
[17] T. Otzen and C. Manterola, “Técnicas de muestreo sobre una población a estudio,” International Jour-nal of Morphology, vol. 35, no. 1, pp. 227–232, 2017, doi: 10.4067/S0717-95022017000100037.
[18] W. J. Doll and G. Torkzadeh, “The measurement of end-user computing satisfaction,” MIS Quarterly, vol. 12, no. 2, pp. 259–274, 1988, doi: 10.2307/248851.
[19] L. R. Aiken, “Three coefficients for analyzing the reliability and validity of ratings,” Educational and Psychological Measurement, vol. 45, no. 1, pp. 131–142, 1985, doi: 10.1177/0013164485451012.
[20] L. M. Escurra, “Cuantificación de la validez de con-tenido por criterio de jueces,” Revista de Psicología, vol. 6, no. 1–2, pp. 103–111, 1988. doi: 10.18800/psico.198801-02.008.
[21] L. J. Cronbach, “Coefficient alpha and the internal structure of tests,” Psychometrika, vol. 16, no. 3, pp. 297–334, 1951, doi: 10.1007/BF02310555.
[22] E. B. Wilson, “Probable inference, the law of succes-sion, and statistical inference,” Journal of the Ame-rican Statistical Association, vol. 22, no. 158, pp. 209–212, 1927, doi: 10.1080/01621459.1927.10502953.