Automatic political discourse analysis with multi-scale convolutional neural networks and contextual data

In this article, the authors propose a new approach to automate the analysis of the political discourse of the citizens and public servants, to allow public administrations to better react to their needs and claims. The tool presented in this article can be applied to the analysis of the underlying...

Full description

Saved in:
Bibliographic Details
Main Authors: Aritz Bilbao-Jayo, Aitor Almeida
Format: Article
Language:English
Published: Wiley 2018-11-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1177/1550147718811827
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849702512055025664
author Aritz Bilbao-Jayo
Aitor Almeida
author_facet Aritz Bilbao-Jayo
Aitor Almeida
author_sort Aritz Bilbao-Jayo
collection DOAJ
description In this article, the authors propose a new approach to automate the analysis of the political discourse of the citizens and public servants, to allow public administrations to better react to their needs and claims. The tool presented in this article can be applied to the analysis of the underlying political themes in any type of text, in order to better understand the reasons behind it. To do so, the authors have built a discourse classifier using multi-scale convolutional neural networks in seven different languages: Spanish, Finnish, Danish, English, German, French, and Italian. Each of the language-specific discourse classifiers has been trained with sentences extracted from annotated parties’ election manifestos. The analysis proves that enhancing the multi-scale convolutional neural networks with context data improves the political analysis results.
format Article
id doaj-art-24dbecb0eb9447e3ab960d6155f4c2c8
institution DOAJ
issn 1550-1477
language English
publishDate 2018-11-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-24dbecb0eb9447e3ab960d6155f4c2c82025-08-20T03:17:36ZengWileyInternational Journal of Distributed Sensor Networks1550-14772018-11-011410.1177/1550147718811827Automatic political discourse analysis with multi-scale convolutional neural networks and contextual dataAritz Bilbao-JayoAitor AlmeidaIn this article, the authors propose a new approach to automate the analysis of the political discourse of the citizens and public servants, to allow public administrations to better react to their needs and claims. The tool presented in this article can be applied to the analysis of the underlying political themes in any type of text, in order to better understand the reasons behind it. To do so, the authors have built a discourse classifier using multi-scale convolutional neural networks in seven different languages: Spanish, Finnish, Danish, English, German, French, and Italian. Each of the language-specific discourse classifiers has been trained with sentences extracted from annotated parties’ election manifestos. The analysis proves that enhancing the multi-scale convolutional neural networks with context data improves the political analysis results.https://doi.org/10.1177/1550147718811827
spellingShingle Aritz Bilbao-Jayo
Aitor Almeida
Automatic political discourse analysis with multi-scale convolutional neural networks and contextual data
International Journal of Distributed Sensor Networks
title Automatic political discourse analysis with multi-scale convolutional neural networks and contextual data
title_full Automatic political discourse analysis with multi-scale convolutional neural networks and contextual data
title_fullStr Automatic political discourse analysis with multi-scale convolutional neural networks and contextual data
title_full_unstemmed Automatic political discourse analysis with multi-scale convolutional neural networks and contextual data
title_short Automatic political discourse analysis with multi-scale convolutional neural networks and contextual data
title_sort automatic political discourse analysis with multi scale convolutional neural networks and contextual data
url https://doi.org/10.1177/1550147718811827
work_keys_str_mv AT aritzbilbaojayo automaticpoliticaldiscourseanalysiswithmultiscaleconvolutionalneuralnetworksandcontextualdata
AT aitoralmeida automaticpoliticaldiscourseanalysiswithmultiscaleconvolutionalneuralnetworksandcontextualdata