Open AccessIntent Classifier Model using Recurrent Neural Networks: a case study to help students with doubts about the functionalities of AVA MOODLE
Author(s) -
Jeferson Oliveira,
Regina Bärwaldt,
Luiz Oscar Homann de Topin,
Joelson Sartori
Publication year - 2021
Publication title -
renote
Language(s) - English
Resource type - Journals
ISSN - 1679-1916
DOI - 10.22456/1679-1916.110230
Subject(s) - chatbot , computer science , artificial neural network , watson , ibm , classifier (uml) , artificial intelligence , world wide web , multimedia , machine learning , materials science , nanotechnology
This survey features an intelligent IBM Watson chatbot to improve student participation in Moodle. Recurrent Neural Networks were used to generate a model and classify the intentions of 48 students who interacted with the assistant. A neural network was trained and submitted to the evaluation criteria and obtained 99.80% precision tests. The virtual assistant also demonstrated the ability to collaborate in student service activities. Infrequently asked questions about the use of Moodle. This study showed evidence that it is feasible to implement the chatbot to help with doubts in these contexts.