A Wizard or a Fool? Initial Assessment of a Wizard of Oz Agent Supporting Collaborative Virtual Environments
Open Access
- 5 December 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 299-301
Abstract
A popular technique for evaluating envisioned AI agents without committing significant engineering resources to implement such an agent is the Wizard of Oz (WoZ) methodology. Thus far, many of the WoZ studies concerned with the design of conversational agents have been standalone systems for individual participants to interact with. The aim of this work was to determine whether a WoZ conversational agent could be embedded within an existing team-based collaborative virtual environment. In doing so, we uncovered a number of potential challenges in designing such a system which may be valuable for those implementing such a system in the future.Keywords
Funding Information
- Australian Department of Defence Human Performance Research Network (ID9024)
- Australian Defence Science and Technology (DST) Group (MyIP8655)
This publication has 8 references indexed in Scilit:
- DesertWoZ: A Wizard of Oz Environment to Support the Design of Collaborative Conversational Agents2022
- Tip of the Finger or Tip of the Tongue?2021
- NottReal2020
- Beyond Dyadic Interactions2019
- The RRADS platform2015
- Wizard of Oz Studies in HRI: A Systematic Review and New Reporting GuidelinesJournal of Human-Robot Interaction, 2012
- SUEDE2001
- An iterative design methodology for user-friendly natural language office information applicationsACM Transactions on Information Systems, 1984