The POTUS Corpus, a database of weekly addresses for the study of stance in politics and virtual agents - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

The POTUS Corpus, a database of weekly addresses for the study of stance in politics and virtual agents

Résumé

One of the main challenges in the field of Embodied Conversational Agent (ECA) is to generate socially believable agents. The common strategy for agent behaviour synthesis is to rely on dedicated corpus analysis. Such a corpus is composed of multimedia files of socio-emotional behaviors which have been annotated by external observers. The underlying idea is to identify interaction information for the agent's socio-emotional behavior by checking whether the intended socio-emotional behavior is actually perceived by humans. Then, the annotations can be used as learning classes for machine learning algorithms applied to the social signals. This paper introduces the POTUS Corpus composed of high-quality audio-video files of political addresses to the American people. Two protagonists are present in this database. First, it includes speeches of former president Barack Obama to the American people. Secondly, it provides videos of these same speeches given by a virtual agent named Rodrigue. The ECA reproduces the original address as closely as possible using social signals automatically extracted from the original one. Both are annotated for social attitudes, providing information about the stance observed in each file. It also provides the social signals automatically extracted from Obama's addresses used to generate Rodrigue's ones.
Fichier principal
Vignette du fichier
2020.lrec-1.193.pdf (1.23 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02873020 , version 1 (18-06-2020)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

  • HAL Id : hal-02873020 , version 1

Citer

Thomas Janssoone, Kevin Bailly, Gael Richard, Chloé Clavel. The POTUS Corpus, a database of weekly addresses for the study of stance in politics and virtual agents. Conference on Language Resources and Evaluation (LREC 2020), 2020, Marseille, France. pp.11 - 16. ⟨hal-02873020⟩
104 Consultations
137 Téléchargements

Partager

Gmail Facebook X LinkedIn More