Clasificador de noticias usando autoencoders

Gonzalo Farias, Sebastian Vergara, Ernesto Fabregas, Gabriel Hermosilla, Sebastian Dormido-Canto, Sebastian Dormido

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

Resumen

This article presents a classification system for news with Deep Learning. With this tool the news are classified in the following categories: Sports, Politics, Economics, Show and Police. Also they receives an scope: Local (Valparaíso), National (Chile) and International (Rest of the World). The classifiers were built using a database with 542 news labeled with the previous criteria. The features were extracted with Autoencoders (AE) to train an Artificial Neural Network (ANN) of multiple classes Softmax (Softmax ANNs). Both stages were stacked following the concept of Deep Learning. The results with the data test (156 news) reach a success rate of 92.3% for the category classifier and 87.2% for the scope classifier. The general success rate for both, category and scope was 83.75%.

Título traducido de la contribuciónNews classifier using autoencoders
Idioma originalEspañol
Título de la publicación alojadaIEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control
Subtítulo de la publicación alojadaTowards an Industry 4.0 - Proceedings
EditoresCarlos Munoz, Gaston Lefranc, Mario Fernandez-Fernandez, Ernesto Rubio, Cristian Duran-Faundez
EditorialInstitute of Electrical and Electronics Engineers Inc.
ISBN (versión digital)9781538655863
DOI
EstadoPublicada - 10 ene. 2019
Publicado de forma externa
EventoIEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0, ICA-ACCA 2018 - Greater Concepcion, Chile
Duración: 17 oct. 201819 oct. 2018

Serie de la publicación

NombreIEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings

Conferencia

ConferenciaIEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0, ICA-ACCA 2018
País/TerritorioChile
CiudadGreater Concepcion
Período17/10/1819/10/18

Palabras clave

  • Autoencoder
  • News Classifier

Huella

Profundice en los temas de investigación de 'Clasificador de noticias usando autoencoders'. En conjunto forman una huella única.

Citar esto