Skip to Main content Skip to Navigation
New interface
Conference papers

A Methodology to Design Human-Like Embodied Conversational Agents

Abstract : This paper presents a bottom-up methodology to study human-human and human-agent dialogues in order to improve the design of embodied conversational agents (ECAs). The methodology uses a matrix representation of dialogues, constructed by means of a (semi-)automatic annotation process. A multidimensional dialogue pattern extraction and a clustering algorithm are applied to the coding matrices. The extracted patterns model the human behaviours.
Complete list of metadata

Cited literature [55 references]  Display  Hide  Download
Contributor : Guillaume Dubuisson Duplessis Connect in order to contact the contributor
Submitted on : Monday, January 13, 2014 - 10:44:19 AM
Last modification on : Wednesday, March 23, 2022 - 11:56:04 AM
Long-term archiving on: : Saturday, April 8, 2017 - 2:38:52 PM


Files produced by the author(s)


  • HAL Id : hal-00927488, version 1


Zacharie Alès, Guillaume Dubuisson Duplessis, Ovidiu Şerban, Alexandre Pauchet. A Methodology to Design Human-Like Embodied Conversational Agents. International Workshop on Human-Agent Interaction Design and Models (HAIDM'12), 2012, Valencia, Spain. online proceedings. ⟨hal-00927488⟩



Record views


Files downloads