Annotating social data with speaker/user engagement. Illustration on online hate characterization in French - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Annotating social data with speaker/user engagement. Illustration on online hate characterization in French

Annoter les données sociales à l'aide de la notion d'engagement. Illustration sur la caractérisation de la haine en ligne en français

Delphine Battistelli
Jade Mekki
  • Fonction : Auteur
  • PersonId : 1249235
  • IdRef : 269295178

Résumé

This paper presents an annotation framework relying on the linguistic notion of speaker/user engagement. This notion is suitable for a finer characterization of online hateful discourse as it allows addressing the following question: does the speaker engage himself to the truthfulness of hate content? Two resources were built to support the annotation framework: a taxonomy of speaker/user engagement degrees and a rich semantic resource of pictograms/emoticons. The paper describes the resources used and the annotation process. Preliminary experiments and results on sexism characterization in French are also presented.
Fichier principal
Vignette du fichier
ICCCN Battistelli et al 2023 Manchester.pdf (3.44 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04279052 , version 1 (10-11-2023)

Identifiants

  • HAL Id : hal-04279052 , version 1

Citer

Delphine Battistelli, Valentina Dragos, Jade Mekki. Annotating social data with speaker/user engagement. Illustration on online hate characterization in French. ICCCN'2023 (International Conference on Computing and Communication Networks), Nov 2023, Manchester (UK), United Kingdom. ⟨hal-04279052⟩
31 Consultations
27 Téléchargements

Partager

Gmail Facebook X LinkedIn More