Implementation of a chatbot based on artificial intelligence language model to respond to frequently asked questions from university students




conversational agent, virtual assistant, university care, GPT, student support


The use of virtual assistants is common in the service processes of different universities around the world. Nowadays, several artificial intelligence tools such as natural language processors are offered for a more efficient development of this service. This article presents the implementation and usability evaluation of a chatbot based on the GPT-3.5-Turbo artificial intelligence language model for the attention of first semester students of Systems Engineering at the National University of Trujillo. The research design was pre-experimental and the chatbot usability questionnaire or CUQ was applied as a research instrument. The results obtained were that the chatbot presents an acceptable level of perceived usability and 93% of students agreed that the answers provided by the virtual assistant were useful. The conversational agent stood out in ease of use and navigation, and also exhibited problems in understanding the questions asked by the user and providing answers in a natural way.


Download data is not yet available.


Bangor, A., Kortum, P. T., & Miller, J. T. (2008). An Empirical Evaluation of the System Usability Scale. International Journal of Human-Computer Interaction, 24(6), 574–594.

Barus, S. P., & Surijati, E. (2022). Chatbot with Dialogflow for FAQ Services in Matana University Library. International Journal of Informatics and Computation, 3(2), 62.

Busch, K., Rochlitzer, A., & Diana Sola, H. L. (2023). Just Tell Me: Prompt Engineering in Business Process Management. Computer Science, 1.

Casazola Cruz, O. D., Alfaro Mariño, G., Burgos Tejada, J., & Ramos More, O. A. (2021). La usabilidad percibida de los chatbots sobre la atención al cliente en las organizaciones: una revisión de la literatura. Interfases, 014, 184–204.

Eloundou, T., Manning, S., Mishkin, P., & Rock, D. (2023). GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models.