Predicting the User Intention in Web Search

  • Gilson dos Reis Dias Fonseca UFJF
  • Jairo Francisco de Souza UFJF
  • Eduardo Barrere UFJF

Resumo


The search for information is inherent to the human being and with the popularization of computers, search systems have become the main source of obtaining knowledge. However, they do not support greater user interaction when they want to do a complex search. It is important to evaluate the user and infer information about him, to know his intention to search to increase the performance of these systems under the principles of SaL. In this paper, we propose a model for classifying the search intention using Transformers. It was used an available dataset and we obtained 97% accuracy in the validation set and 99% f-measure in the test set, achieving better results when comparing to traditional methods.
Palavras-chave: searching as learning, transformers, exploratory search, information retrieval
Publicado
05/11/2021
FONSECA, Gilson dos Reis Dias; SOUZA, Jairo Francisco de; BARRERE, Eduardo. Predicting the User Intention in Web Search. In: BRAZILIAN SYMPOSIUM ON MULTIMEDIA AND THE WEB (WEBMEDIA), 1. , 2021, Minas Gerais. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . p. 133-136.