Adapting sentiment analysis to face-to-face human-agent interactions: from detection to evaluation issues

Abstract :

This paper introduces a sentiment analysis method suitable to the human-agent and face-to-face interactions. We present the positioning of our system and its evaluation protocol according to the existing sentiment analysis literature and detail how the proposed system integrates the human-agent interaction issues. Finally, we provide an in-depth analysis of the results obtained by the evaluation, opening the discussion on the different difficulties and the remaining challenges of sentiment analysis in human-agent interactions.

Type de document :
Communication dans un congrès
ACII 2015, Aug 2015, Qian, China. 2015
Liste complète des métadonnées

https://hal-imt.archives-ouvertes.fr/hal-01259917
Contributeur : Admin Télécom Paristech <>
Soumis le : jeudi 21 janvier 2016 - 11:44:11
Dernière modification le : jeudi 11 janvier 2018 - 06:23:39

Identifiants

  • HAL Id : hal-01259917, version 1

Citation

Caroline Langlet, C. Clavel. Adapting sentiment analysis to face-to-face human-agent interactions: from detection to evaluation issues. ACII 2015, Aug 2015, Qian, China. 2015. 〈hal-01259917〉

Partager

Métriques

Consultations de la notice

96