DOI:
https://doi.org/10.14483/22487638.22808Publicado:
31-03-2025Número:
Vol. 29 Núm. 83 (2025): Enero - MarzoSección:
RevisiónExplorando el uso de inteligencia artificial generativa para el desarrollo de chatbots para portales web universitarios: un mapeo sistemático
Exploring the use of generative artificial intelligence for the development of chatbots for university web portals: A systematic mapping
Palabras clave:
Generative artificial intelligence, Chatbots, Systematic map (en).Palabras clave:
inteligencia artificial generativa, chatbots, mapeo sistemático (es).Descargas
Resumen (es)
Contexto: los chatbots con inteligencia artificial generativa (GAI, por su sigla en inglés) han evolucionado significativamente, impulsados por avances sobre grandes modelos de lenguaje (LLM, por su sigla en inglés). Estos
sistemas ofrecen interacciones más naturales y adaptativas, a la vez que transforman diversos sectores y plantean nuevos desafíos tecnológicos y éticos.
Objetivo: identificar las principales tendencias, oportunidades y desafíos en el desarrollo de chatbots con GAI en los últimos años.
Metodología: se realizó un mapeo sistemático adaptado, por medio del cual se analizó el uso de GAI en chatbots.
Se definieron tres preguntas de investigación y se hizo una búsqueda exhaustiva en las bases Web of Science, Scopus
y ScienceDirect. Los estudios fueron clasificados para responder a las preguntas de investigación.
Resultados: los sectores de educación y salud son los más investigados, en los que se destaca el uso de LLM como
GPT-4 (generative pre-trained transformer), para personalización del aprendizaje y apoyo en salud mental, por ejemplo. También se identificaron aplicaciones en tecnología, comercio e industria. Los modelos de OpenAI son los predominantes, aunque existen alternativas especializadas. Los principales desafíos incluyen alucinaciones", necesidad de supervisión humana, sesgos y altos costos computacionales.
Conclusiones: la flexibilidad y rendimiento de modelos como GPT-4 los posicionan como opciones prominentes para implementaciones de chatbots. Los desafíos identificados son cruciales para guiar un desarrollo efectivo, para así considerar oportunidades y limitaciones actuales
Resumen (en)
Context: Generative artificial intelligence (GAI) chatbots have evolved significantly, driven by advances in large language models (LLM). These systems offer more natural and adaptive interactions, transforming various industries and posing new technological and ethical challenges.
Objective: Identify the main trends, opportunities and challenges in the development of chatbots with GAI in recent years.
Methodology: An adapted systematic mapping was conducted, analyzing the use of GAI in chatbots. Three research questions were defined and an exhaustive search was carried out in Web of Science, Scopus, and ScienceDirect databases. The studies were classified to answer the research questions.
Results: The education and health sectors are the most researched, highlighting the use of LLM such as GPT-4
for learning personalization and mental health support. Applications in technology, commerce, and industry were
also identified. OpenAI models are dominant, although specialized alternatives exist. The main challenges include
"hallucinations,"the need for human supervision, biases, and high computational costs.
Conclusions: The flexibility and performance of models like GPT-4 position them as prominent options for chatbot
implementations. The identified challenges are crucial for guiding effective development, considering current
opportunities and limitations.
Referencias
Abubakar, A. M., Gupta, D., y Parida, S. (2024). A reinforcement learning approach for intelligent conversational chatbot for enhancing mental health therapy. Procedia Computer Science, 235, 916-925. https://doi.org/10.1016/j.procs.2024.04.087
Alotaibi, J. O., y Alshahre, A. S. (2024). The role of conversational AI agents in providing support and social care for isolated individuals. Alexandria Engineering Journal, 108, 273-284. https://doi.org/10.1016/j.aej.2024.07.098
Anil, R., Dai, A. M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z., Chu, E., Clark, J. H., Shafey, L. El, Huang, Y., Meier-Hellstern, K., Mishra, G., Moreira, E., Omernick, M., Robinson, K., . . . Wu, Y. (2023). PaLM 2 Technical Report. arXiv:2305.10403. https://doi.org/10.48550/arXiv.2305.10403
Bečulić, H., Begagić, E., Skomorac, R., Mašović, A., Selimović, E., y Pojskić, M. (2024). ChatGPT's contributions to the evolution of neurosurgical practice and education: a systematic review of benefits, concerns and limitations. Medicinski Glasnik, 21(1), 126-131. https://doi.org/10.17392/1661-23
Bengesi, S., El-Sayed, H., Sarker, M. K., Houkpati, Y., Irungu, J., y Oladunni, T. (2024). Advancements in Generative AI: a comprehensive review of GANs, GPT, autoencoders, diffusion model, and transformers. IEEE Access, 12, 69812-69837. https://doi.org/10.1109/access.2024.3397775
Brown, A., Kumar, A. T., Melamed, O., Ahmed, I., Wang, Y. H., Deza, A., Morcos, M., Zhu, L., Maslej, M., Minian, N., Sujaya, V., Wolff, J., Doggett, O., Iantorno, M., Ratto, M., Selby, P., y Rose, J. (2023). A motivational interviewing chatbot with generative reflections for increasing readiness to quit smoking: iterative development study. JMIR Mental Health, 10, e49132. https://doi.org/10.2196/49132
Cahyana, D., Hadiarto, A., Irawan, N., Hati, D. P., Pratamaningsih, M. M., Karolinoerita, V., Mulyani, A., Sukarman, N., Hikmat, M., Ramadhani, F., Gani, R. A., Yatno, E., Heryanto, R. B., Suratman, N., Gofar, N., y Suriadikusumah, A. (2024). Application of ChatGPT in soil science research and the perceptions of soil scientists in Indonesia. Artificial Intelligence in Geosciences, 5, 100078. https://doi.org/10.1016/j.aiig.2024.100078
Cascella, M., Semeraro, F., Montomoli, J., Bellini, V., Piazza, O., y Bignami, E. (2024a). The breakthrough of large language models release for medical applications: 1-year timeline and perspectives. Journal of Medical Systems, 48(1). https://doi.org/10.1007/s10916-024-02045-3
Chen, Z., Xu, L., Zheng, H., Chen, L., Tolba, A., Zhao, L., Yu, K., y Feng, H. (2024). Evolution and prospects of foundation models: From large language models to large multimodal models. *Computers, Materials y Continua/Computers, Materials y Continua (Print), 80*(2), 1753-1808. https://doi.org/10.32604/cmc.2024.052618
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H.W., Sutton, C., Gehrmann, S., Schuh, P., Shi, K., Tsvyashchenko, S., Maynez, J., Rao, A., Barnes, P., Tay, Y., Shazeer, N., Prabhakaran, V., . . . Fiedel, N. (2022). PaLM: scaling language modeling with pathways. arXiv:2204.02311. https://doi.org/10.48550/arXiv.2204.02311
Chowdhury, A. K., Sujon, Md. S. R., Shafi, Md. S. S., Ahmmad, T., Ahmed, S., Hasib, K. M., y Shah, F. M. (2024). Harnessing large language models over transformer models for detecting Bengali depressive social media text: a comprehensive study. Natural Language Processing Journal, 7, 100075. https://doi.org/10.1016/j.nlp.2024.100075
Drelick, A. M., Woodfield, C., y Freedman, J. E. (2024). Educational chatbot development informed by clinical simulations. Interactive Learning Environments, 33(3), 2044-2055. https://doi.org/10.1080/10494820.2024.2388782
Dubravova, H., Cap, J., Holubova, K., y Hribnak, L. (2024). Artificial intelligence as an innovative element of support in policing. Procedia Computer Science, 237, 237-244. https://doi.org/10.1016/j.procs.2024.05.101
Escalante, J., Pack, A., y Barrett, A. (2023). AI-generated feedback on writing: insights into efficacy and ENL student preference. International Journal of Educational Technology in Higher Education, 20(1), 57. https://doi.org/10.1186/s41239-023-00425-2
Gill, S. S., y Kaur, R. (2023). ChatGPT: Vision and challenges. *Internet of Things and Cyber-Physical Systems, 3*, 262-271. https://doi.org/10.1016/j.iotcps.2023.05.004
Haleem, A., Javaid, M., y Singh, R. P. (2024). Exploring the competence of ChatGPT for customer and patient service management. Intelligent Pharmacy, 2(3), 392-414. https://doi.org/10.1016/j.ipha.2024.03.002
Heston, T. F. (2023). Safety of large language models in addressing depression. Cureus. https://doi.org/10.7759/cureus.50729
Ilagan, J. B., y Ilagan, J. R. (2024). A prototype of a conversational virtual university support agent powered by a large language model that addresses inquiries about policies in the student handbook. Procedia Computer Science, 239, 1124-1131. https://doi.org/10.1016/j.procs.2024.06.278
Javaid, M., Haleem, A., y Singh, R. P. (2023). ChatGPT for healthcare services: an emerging stage for an innovative perspective. BenchCouncil Transactions on Benchmarks Standards and Evaluations, 3(1), 100105. https://doi.org/10.1016/j.tbench.2023.100105
Javaid, M., Haleem, A., Singh, R. P., Khan, S., y Khan, I. H. (2023). Unlocking the opportunities through ChatGPT Tool towards ameliorating the education system. BenchCouncil Transactions on Benchmarks Standards and Evaluations, 3(2), 100115. https://doi.org/10.1016/j.tbench.2023.100115
Kim, K., Cho, K., Jang, R., Kyung, S., Lee, S., Ham, S., Choi, E., Hong, G.-S., y Kim, N. (2024a). Updated primer on generative artificial intelligence and large language models in medical imaging for medical professionals. Korean Journal of Radiology, 25(3), 224. https://doi.org/10.3348/kjr.2023.0818
Kitchenham, B., y Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering (Technical report EBSE 2007-001). Keele University y Durham University.
Labouchère, A., y Raffoul, W. (2024). ChatGPT and Bard in plastic surgery: hype or hope? Surgeries, 5(1), 37-48. https://doi.org/10.3390/surgeries5010006
Li, C., Wong, C., Zhang, S., Usuyama, N., Liu, H., Yang, J., Naumann, T., Poon, H., y Gao, J. (2023). LLAVA-MeD: training a large language-and-vision assistant for biomedicine in one day. arXiv:2306.00890. https://doi.org/10.48550/arxiv.2306.00890
Li, Y., Li, Z., Zhang, K., Dan, R., Jiang, S., y Zhang, Y. (2023). ChatDoctor: a medical chat model fine-tuned on a large language model Meta-AI (LLAMA) using medical domain knowledge. Cureus. https://doi.org/10.7759/cureus.40895
Liu, Y., Han, T., Ma, S., Zhang, J., Yang, Y., Tian, J., He, H., Li, A., He, M., Liu, Z., Wu, Z., Zhao, L., Zhu, D., Li, X., Qiang, N., Shen, D., Liu, T., y Ge, B. (2023). Summary of ChatGPT-related research and perspective towards the future of large language models. *Meta-Radiology, 1*(2), 100017. https://doi.org/10.1016/j.metrad.2023.100017
Lozić, E., y Štular, B. (2023). Fluent but not factual: a comparative analysis of ChatGPT and other AI chatbots' proficiency and originality in scientific writing for humanities. Future Internet, 15(10), 336. https://doi.org/10.3390/fi15100336
Madunić, J., y Sovulj, M. (2024). Application of ChatGPT in information literacy instructional design. Publications, 12(2), 11. https://doi.org/10.3390/publications12020011
Medeiros, T., Medeiros, M., Azevedo, M., Silva, M., Silva, I., y Costa, D. G. (2023). Analysis of language-model-powered chatbots for query resolution in PDF-based automotive manuals. Vehicles, 5(4), 1384-1399. https://doi.org/10.3390/vehicles5040076
Meskó, B., y Topol, E. J. (2023). The imperative for regulatory oversight of large language models (or generative AI) in healthcare. Npj Digital Medicine, 6(1). https://doi.org/10.1038/s41746-023-00873-0
Pan, L., Zhao, Z., Lu, Y., Tang, K., Fu, L., Liang, Q., y Peng, S. (2024). Opportunities and challenges in the application of large artificial intelligence models in radiology. *Meta-Radiology, 2*(2), 100080. https://doi.org/10.1016/j.metrad.2024.100080
Parra, V., Sureda, P., Corica, A., Schiaffino, S., y Godoy, D. (2024). Can generative AI solve geometry problems? Strengths and weaknesses of LLM for geometric reasoning in spanish. International Journal of Interactive Multimedia and Artificial Intelligence, (en prensa), 1. https://doi.org/10.9781/ijimai.2024.02.009
Petersen K., Feldt, R., Mujtaba, S., y Mattsson, M. (2008, junio 26-27). Systematic mapping studies in software engineering [Conferencia]. 12th International Conference on Evaluation and Assessment in Software Engineering (EASE), University of Bari, Italy.
Popovici, M.-D. (2023). ChatGPT in the classroom. Exploring its potential and limitations in a functional programming course. *International Journal of Human-Computer Interaction, 40*(22), 7743-7754. https://doi.org/10.1080/10447318.2023.2269006
Prasad, S., Gupta, H., y Ghosh, A. (2024). Leveraging the potential of large language models. Informatica, 48(8), 1-16. https://doi.org/10.31449/inf.v48i8.5635
Prebble, T., Hargraves, H., Leach, L., Naidoo, K., Suddaby, G., y Zepke, N. (2004). Impact of student support services and academic development programmes on student outcomes in undergraduate tertiary study. Ministry of Education Wellington.
Raj, R., Singh, A., Kumar, V., y Verma, P. (2023). Analyzing the potential benefits and use cases of ChatGPT as a tool for improving the efficiency and effectiveness of business operations. BenchCouncil Transactions on Benchmarks Standards and Evaluations, 3(3), 100140. https://doi.org/10.1016/j.tbench.2023.100140
Roumeliotis, K. I., Tselikas, N. D., y Nasiopoulos, D. K. (2024). LLM in e-commerce: a comparative analysis of GPT and LLaMA models in product review evaluation. Natural Language Processing Journal, 6, 100056. https://doi.org/10.1016/j.nlp.2024.100056
Saka, A., Taiwo, R., Saka, N., Salami, B. A., Ajayi, S., Akande, K., y Kazemi, H. (2024). GPT models in construction industry: opportunities, limitations, and a use case validation. Developments in the Built Environment, 17, 100300. https://doi.org/10.1016/j.dibe.2023.100300
Scanlon, M., Breitinger, F., Hargreaves, C., Hilgert, J.-N., y Sheppard, J. (2023). ChatGPT for digital forensic investigation: the good, the bad, and the unknown. Forensic Science International Digital Investigation, 46, 301609. https://doi.org/10.1016/j.fsidi.2023.301609
Schweitzer, S., y Conrads, M. (2024). The digital transformation of jurisprudence: an evaluation of ChatGPT-4's applicability to solve cases in business law. Artificial Intelligence and Law. https://doi.org/10.1007/s10506-024-09406-w
Seeman, E. D., y O'Hara, M. (2006). Customer relationship management in higher education. *Campus-Wide Information Systems, 23*(1), 24-34. https://doi.org/10.1108/10650740610639714
Sohail, S. S., Farhat, F., Himeur, Y., Nadeem, M., Madsen, D. Ø., Singh, Y., Atalla, S., y Mansoor, W. (2023). Decoding ChatGPT: a taxonomy of existing research, current challenges, and possible future directions. *Journal of King Saud University - Computer and Information Sciences, 35*(8), 101675. https://doi.org/10.1016/j.jksuci.2023.101675
Suryanto, T. L. M., Wibawa, A. P., Hariyono, H., y Nafalski, A. (2023). Evolving conversations: a review of chatbots and implications in natural language processing for cultural heritage ecosystems. International Journal of Robotics and Control Systems, 3(4), 955-1006. https://doi.org/10.31763/ijrcs.v3i4.1195
Vandelanotte, C., Trost, S., Hodgetts, D., Imam, T., Rashid, M., To, Q. G., y Maher, C. (2023). Increasing physical activity using a just-in-time adaptive digital assistant supported by machine learning: a novel approach for hyper-personalised mHealth interventions. Journal of Biomedical Informatics, 144, 104435. https://doi.org/10.1016/j.jbi.2023.104435
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., y Polosukhin, I. (2023). Attention is all you need. arXiv:1706.03762. https://doi.org/10.48550/arXiv.1706.03762
Wang, Y.-C., Xue, J., Wei, C., y Kuo, C. J. (2023). An overview on generative AI at scale with edge-cloud computing. IEEE Open Journal of the Communications Society, 4, 2952-2971. https://doi.org/10.1109/ojcoms.2023.3320646
Westphal, E., y Seitz, H. (2024). Generative artificial intelligence: analyzing its future applications in additive manufacturing. Big Data and Cognitive Computing, 8(7), 74. https://doi.org/10.3390/bdcc8070074
Wilendra, W., Nadlifatin, R., y Kusumawulan, C. K. (2024). ChatGPT: the AI game-changing revolution in marketing strategy for the indonesian cosmetic industry. Procedia Computer Science, 234, 1012-1019. https://doi.org/10.1016/j.procs.2024.03.091
Wölfel, M., Shirzad, M. B., Reich, A., y Anderer, K. (2023). Knowledge-based and generative-AI-driven pedagogical conversational agents: a comparative study of Grice's cooperative principles and trust. Big Data and Cognitive Computing, 8(1), 2. https://doi.org/10.3390/bdcc8010002
Yager, K. G. (2023). Domain-specific chatbots for science using embeddings. Digital Discovery, 2(6), 1850-1861. https://doi.org/10.1039/d3dd00112a
Yang, Z., Khatibi, E., Nagesh, N., Abbasian, M., Azimi, I., Jain, R., y Rahmani, A. M. (2024). ChatDiet: empowering personalized nutrition-oriented food recommender chatbots through an LLM-augmented framework. Smart Health, 32, 100465. https://doi.org/10.1016/j.smhl.2024.100465
Yik, B. J., y Dood, A. J. (2024). ChatGPT convincingly explains organic chemistry reaction mechanisms slightly inaccurately with high levels of explanation sophistication. Journal of Chemical Education, 101(5), 1836-1846. https://doi.org/10.1021/acs.jchemed.4c00235
Zhu, S., Wang, Z., Zhuang, Y., Jiang, Y., Guo, M., Zhang, X., y Gao, Z. (2024). Exploring the impact of ChatGPT on art creation and collaboration: benefits, challenges and ethical implications. Telematics and Informatics Reports, 14, 100138. https://doi.org/10.1016/j.teler.2024.100138
Cómo citar
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Descargar cita
Licencia
Derechos de autor 2025 Arnold Steeven Catamuscay Pérez, Cristian Eduardo Núñez Valencia, Hugo Armando Ordóñez Erazo
Esta obra está bajo una licencia internacional Creative Commons Atribución-CompartirIgual 4.0.
Esta licencia permite a otros remezclar, adaptar y desarrollar su trabajo incluso con fines comerciales, siempre que le den crédito y concedan licencias para sus nuevas creaciones bajo los mismos términos. Esta licencia a menudo se compara con las licencias de software libre y de código abierto “copyleft”. Todos los trabajos nuevos basados en el tuyo tendrán la misma licencia, por lo que cualquier derivado también permitirá el uso comercial. Esta es la licencia utilizada por Wikipedia y se recomienda para materiales que se beneficiarían al incorporar contenido de Wikipedia y proyectos con licencias similares.
