Communication Dans Un Congrès Année : 2024

Exploring the Emotional Dimension of French Online Toxic Content

Explorer la dimension émotionnelle des contenus toxiques en Français

Résumé

One of the biggest hurdles for the effective analysis of data collected on social platforms is the need for deeper insights on the content of this data. Emotion annotation can bring new perspectives on this issue and can enable the identification of content-specific features. This study aims at investigating the ways in which variation in online toxic content can be explored through emotions detection . The paper describes the emotion annotation of three different corpora in French which all belong to toxic content (extremist content, sexist content and hateful content respectively). To this end, first a fine-grained annotation parser of emotions was used to automatically annotate the data sets. Then, several empirical studies were carried out to characterize the content in the light of obtained emotional categories. Results suggest that emotion annotations can provide new insights for online content analysis and stronger empirical background for automatic toxic content detection.

Fichier principal
Vignette du fichier
DTIS2024-091-2024-Publiée.pdf (312.45 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-04718625 , version 1 (02-10-2024)

Licence

Identifiants

  • HAL Id : hal-04718625 , version 1

Citer

Valentina Dragos, Delphine Battistelli, Fatou Sow, Aline Etienne. Exploring the Emotional Dimension of French Online Toxic Content. LREC COLING 2024, May 2024, Turin, Italy. ⟨hal-04718625⟩
91 Consultations
130 Téléchargements

Partager

  • More