Semantically Time Tracking of Events from Web Documents

  • Welton Santos UFSJ
  • Elverton Fazzion UFSJ
  • Diego Dias UFSJ
  • Marcelo Guimarães UNIFESP
  • Elisa Tuler UFSJ
  • Leonardo Rocha UFSJ

Resumo


Exploring large news collections created by media outlets with traditional search engines is impractical for demanding users. We propose a temporal exploration tool that aims to facilitate the consultation of news collections. We concentrated our efforts on two fronts: (i) allowing users to make queries with the addition of information from documents represented by word embbedings, and; (ii) retrieving temporal information to generate timelines presented by an appropriate interface. We evaluated our solution in a collection of a Brazilian newspaper, demonstrating that it can draw different timelines, covering different subtopics of the same theme.
Palavras-chave: Tracking Events, Word Embeedings, Search Engines
Publicado
05/11/2021
SANTOS, Welton; FAZZION, Elverton; DIAS, Diego; GUIMARÃES, Marcelo; TULER, Elisa; ROCHA, Leonardo. Semantically Time Tracking of Events from Web Documents. In: SIMPÓSIO BRASILEIRO DE SISTEMAS MULTIMÍDIA E WEB (WEBMEDIA), 1. , 2021, Minas Gerais. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . p. 141-144.

##plugins.generic.recommendByAuthor.heading##

1 2 > >>