No Cover Image

Conference Paper/Proceeding/Abstract 84 views

Towards Co-designing a Human-Agent Interface: A Case Study in Online Grooming Detection.

Peter Daish, Nicholas Micallef Orcid Logo, Nuria Lorenzo-Dus Orcid Logo, Adeline Paiement Orcid Logo, Deepak Sahoo Orcid Logo

Proceedings of the 12th International Conference on Human-Agent Interaction, Pages: 390 - 392

Swansea University Authors: Peter Daish, Nicholas Micallef Orcid Logo, Nuria Lorenzo-Dus Orcid Logo, Adeline Paiement Orcid Logo, Deepak Sahoo Orcid Logo

Full text not available from this repository: check for access using links below.

DOI (Published version): 10.1145/3687272.3690893

Abstract

We present a methodology for co-designing a human-agent interface and a case study in online grooming detection for incorporating multiple-stakeholders perspectives into the design of human-agent platforms, with the goal of establishing a common dialogue between the stakeholders. We propose that ite...

Full description

Published in: Proceedings of the 12th International Conference on Human-Agent Interaction
ISBN: 979-8-4007-1178-7
Published: New York, NY, USA ACM 2024
URI: https://cronfa.swan.ac.uk/Record/cronfa68341
Abstract: We present a methodology for co-designing a human-agent interface and a case study in online grooming detection for incorporating multiple-stakeholders perspectives into the design of human-agent platforms, with the goal of establishing a common dialogue between the stakeholders. We propose that iterative co-design techniques staged in a provotypical fashion could successfully capture and overcome tensions between stakeholders perspectives on how human-agent interactions ought to be manifested. Our initial work found that our iterative co-design framework could be successful in resolving these tensions. However, multiple design iterations that focus on finding compromises between stakeholders can lead to acceptance of novel interaction designs.
Item Description: Poster
College: Faculty of Science and Engineering
Start Page: 390
End Page: 392