Embodied conversational agent Jack for restaurant-context English conversation practice

Design · All designs
Evidence · no claims cited

Description

The system is an embodied conversational agent, personified as Jack, implemented with the Unity game engine front-end and Node.js back-end, built on the authors' previous work. It supports spoken dialogues in a restaurant context where learners are welcomed, guided to a table, order drinks and dishes, and request the bill. Speech recognition is performed by external services (Wit.ai and Dialogflow) that turn utterances into intents and entities with confidence scores. Jack also uses non-verbal backchannels like gaze, head nods, smiles, and blinking.

Design Implications

Context

Requirements

• Intents for the conversation domain must be defined beforehand on the Wit.ai or Dialogflow platform so they can be identified from learner utterances

Constraints

• The conversation is domain-specific (restaurant scenario); the dialogue script is written in XML and can be modified to target a different conversation context

Target Learners

• Japanese EFL learners at a university

Learning Goals

• Practicing daily English conversation and increasing willingness to communicate in L2

Claims

Related Designs

• Conversational pedagogical agent with AI-driven dialogue, lip-synchronised audio and conversation memory
• DiMaCA: a dialogue management model combining communication strategies and affective backchannels to foster WTC-friendly agent conversations
• Phoenix: a voice-based, non-embodied LLM conversational peer agent for group learning

Examples

-

Key Sources

• Emmanuel Ayedoun, Yuki Hayashi, Kazuhisa Seta. (2018). Adding Communicative and Affective Strategies to an Embodied Conversational Agent to Enhance Second Language Learners' Willingness to Communicate. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-018-0171-6

Page metadata

Field	Value
type	design
id	eca-jack-restaurant-l2-agent
title	Embodied conversational agent Jack for restaurant-context English conversation practice
description	The system is an embodied conversational agent, personified as Jack, implemented with the Unity game engine front-end and Node.js back-end, built on the authors' previous work.
status	review
generated	by process:settle-candidates on 2026-10-28
trust	unverified — no one has confirmed this page's content
sources	1 — emmanuel-ayedoun-2018

Frontmatter is the page's machine-readable record — see the Schema & Guide.