Izvorni znanstveni članak
Improving user experience by ANN prediction and NLP chatbot
Diana Bratić
orcid.org/0000-0003-0631-2905
; Sveučilište u Zagrebu Grafički fakultet
Kristina Puhanić
; Sveučilište u Zagrebu Grafički fakultet
Denis Jurečić
; Sveučilište u Zagrebu Grafički fakultet
Sažetak
As communication between service providers and users increases daily due to the large supply
and demand for services, the application of artificial intelligence in business domains can greatly
facilitate and improve characteristics such as the speed and efficiency of communication through
the implementation of NLP chatbots presented in this work. This work aims to investigate the
consequences of NLP chatbot implementation and the reliability of ANN prediction in terms of
user experience, and to determine whether the developed NLP chatbot application matches the
ingenuity in understanding communication in terms of algorithm reliability. It also aims to verify
whether differences in the improvement of the user experience by NLP chatbots can be detected
through a comparative analysis and what impact the speed of NLP chatbots has on the user experience
compared to a chatbot without NLP function.
The programming of the application and the simulation were done with the Python programming
language in the PyCharm integrated development environment using the artificial neural network
model and libraries such as PyTorch, NLTK and Tkinter. The creation of the experimental part
consisted of the creation of an NLP chatbot application, the creation of a simple chatbot represented
by a simulation display, and the carrying out a comparative analysis between an NLP chatbot and a
rule-based chatbot.
The proposed model, primarily the principle itself, can be used for other domains that could
significantly utility from the implementation of NLP chatbots, and not only for the domains
highlighted in this paper.
Ključne riječi
NLP, chatbot, AI, user experience, PyTorch
Hrčak ID:
300904
URI
Datum izdavanja:
28.4.2023.
Posjeta: 367 *