Pan: conversational agent for criminal investigations

Hepenstal, Sam, Zhang, Leishi ORCID logoORCID: https://orcid.org/0000-0002-3158-2328, Kodagoda, Neesha and Wong, B. L. William ORCID logoORCID: https://orcid.org/0000-0002-3363-0741 (2020) Pan: conversational agent for criminal investigations. IUI '20: Proceedings of the 25th International Conference on Intelligent User Interfaces Companion. In: IUI '20: 25th International Conference on Intelligent User Interfaces, 17-20 Mar 2020, Cagliari, Italy. ISBN 9781450375139. [Conference or Workshop Item] (doi:10.1145/3379336.3381463)

[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (658kB) | Preview

Abstract

We present an early prototype conversational agent (CA), called Pan, for retrieving information to support criminal investigations. Our approach tackles the issue of algorithmic transparency, which is critical in unpredictable, high risk, and high consequence domains. We present a novel method to flexibly model CA intentions and provide transparency of attributes that is underpinned with human recognition. We propose that Pan can be used for experimentation to probe analyst requirements and to evaluate the effectiveness of our explanation structure.

Item Type: Conference or Workshop Item (Paper)
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 29593
Notes on copyright: © 2020 Copyright held by the owner/author(s). This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in IUI '20: Proceedings of the 25th International Conference on Intelligent User Interfaces Companion, http://dx.doi.org/10.1145/3379336.3381463
Useful Links:
Depositing User: Jisc Publications Router
Date Deposited: 15 Apr 2020 08:44
Last Modified: 29 Nov 2022 18:32
URI: https://eprints.mdx.ac.uk/id/eprint/29593

Actions (login required)

View Item View Item

Statistics

Activity Overview
6 month trend
292Downloads
6 month trend
249Hits

Additional statistics are available via IRStats2.