Affective Interaction with a Companion Robot for Hospitalized Children: a Linguistically based Model for Emotion Detection - Archive ouverte HAL Access content directly
Conference Papers Year : 2011

Affective Interaction with a Companion Robot for Hospitalized Children: a Linguistically based Model for Emotion Detection

(1) , (1, 2) , (3) , (3)
1
2
3

Abstract

This paper presents a system which aims at characterizing emotions in speech by only considering linguistic content. It is based on the assumption that emotions can be compound: simple lexical words have an intrinsic emotional value, while verbal and adjectival predicates act as a function on the emotional values of their arguments. The paper describes the compositional computation algorithm of the emotion, as well as the lexical emotional lexicons used by this algorithm. A quantitative and qualitative analysis of the differences between system outputs and expert annotations is given, which shows satisfactory results, with a good detection of emotional valence in 82.8% of the test utterances.
Fichier principal
Vignette du fichier
LTC_MLT_Emologus.pdf (224.52 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00664618 , version 1 (01-02-2012)

Identifiers

  • HAL Id : hal-00664618 , version 1

Cite

Marc Le Tallec, Jean-Yves Antoine, Jeanne Villaneau, Dominique Duhaut. Affective Interaction with a Companion Robot for Hospitalized Children: a Linguistically based Model for Emotion Detection. 5th Language and Technology Conference (LTC'2011), Nov 2011, Poznan, Poland. 6 p. ⟨hal-00664618⟩
355 View
172 Download

Share

Gmail Facebook Twitter LinkedIn More