Intent Classifier Model using Recurrent Neural Networks: a case study to help students with doubts about the functionalities of AVA MOODLE

Autores

  • Jeferson Oliveira FURG
  • Regina Barwaldt FURG
  • Luiz Oscar Homann de Topin FURG
  • Joelson Sartori FURG

DOI:

https://doi.org/10.22456/1679-1916.110230

Palavras-chave:

Assistente virtual, IBM Watson, Ambiente Virtual de Aprendizagem, Redes Neurais Recorrentes.

Resumo

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.

Downloads

Não há dados estatísticos.

Downloads

Publicado

2021-01-04

Como Citar

OLIVEIRA, J.; BARWALDT, R.; OSCAR HOMANN DE TOPIN, L.; SARTORI, J. Intent Classifier Model using Recurrent Neural Networks: a case study to help students with doubts about the functionalities of AVA MOODLE. Revista Novas Tecnologias na Educação, Porto Alegre, v. 18, n. 2, p. 215–224, 2021. DOI: 10.22456/1679-1916.110230. Disponível em: https://seer.ufrgs.br/index.php/renote/article/view/110230. Acesso em: 18 abr. 2024.

Edição

Seção

Inteligência Artificial na Educação