Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation
Journal articles

Que peuvent les algorithmes de plongement de mots pour l’analyse sociologique des textes ? Analyser les discours et caractériser les locuteurs des plateformes « Grand Débat National » et « Vrai Débat »

Abstract : In this contribution we propose to contribute to the evaluation of algorithms called “word embedding” to the sociological analysis of texts: on the one hand, by comparing the results of semantic analyses of these algorithms with the now well-known approaches of textual data analysis; on the other hand, by focusing on what constitutes one of the main obstacles to the sociological analysis of the web: the difficulty to sociologically characterize the authors of statements from the web. To do this, we analyze the statements coming from two platforms of “civic tech” – the governmental platform, the “Grand Débat National”, and its political and algorithmic response proposed by a collective of Yellow Vests, the “Vrai Débat”. A third corpus from the “Entendre la France” platform, with the same design as that of the “Grand Débat National” and documented in terms of socio-political properties, will allow us to characterize the speakers according to their discourse and to try to predict, using machine learning approaches, the “pseudo properties” assigned to the speakers of the “Grand Débat National”.
Complete list of metadata

https://halshs.archives-ouvertes.fr/halshs-03372892
Contributor : Mathieu Brugidou Connect in order to contact the contributor
Submitted on : Monday, October 11, 2021 - 11:02:48 AM
Last modification on : Saturday, June 25, 2022 - 8:06:16 PM

Identifiers

  • HAL Id : halshs-03372892, version 1

Collections

UGA | CNRS | PACTE | EDF

Citation

Suignard Philippe, Caroline Escoffier, Lou Charaudeau, Mathieu Brugidou. Que peuvent les algorithmes de plongement de mots pour l’analyse sociologique des textes ? Analyser les discours et caractériser les locuteurs des plateformes « Grand Débat National » et « Vrai Débat ». Statistique et Société, Société française de statistique, 2021, Gilets jaunes et Grand Débat National : outils, données et analyses., 9 (1-2), pp.133-145. ⟨halshs-03372892⟩

Share

Metrics

Record views

51