How analysts think: a preliminary study of human needs and demands for AI-based conversational agents

Hepenstal, Sam, Wong, B. L. William ORCID: https://orcid.org/0000-0002-3363-0741, Zhang, Leishi ORCID: https://orcid.org/0000-0002-3158-2328 and Kodagoda, Neesha (2019) How analysts think: a preliminary study of human needs and demands for AI-based conversational agents. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 63 (1) . pp. 178-182. ISSN 2169-5067 (doi:10.1177/1071181319631333)

[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (271kB) | Preview

Abstract

For conversational agents to provide benefit to intelligence analysis they need to be able to recognise and respond to the analysts intentions. Furthermore, they must provide transparency to their algorithms and be able to adapt to new situations and lines of inquiry. We present a preliminary analysis as a first step towards developing conversational agents for intelligence analysis: that of understanding and modeling analyst intentions so they can be recognised by conversational agents. We describe in-depth interviews conducted with experienced intelligence analysts and implications for designing conversational agent intentions using Formal Concept Analysis.

Item Type: Article
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 28369
Notes on copyright: Hepenstal, S., Wong, B. L. W., Zhang, L., & Kodogoda, N. (2019). How analysts think: A preliminary study of human needs and demands for AI-based conversational agents. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 63(1), 178–182. Copyright © 2019 by Human Factors and Ergonomics Society and © Crown copyright (2019), Dstl. DOI: https://doi.org/10.1177/1071181319631333
Useful Links:
Depositing User: Leishi Zhang
Date Deposited: 28 Nov 2019 09:15
Last Modified: 21 Apr 2020 13:49
URI: https://eprints.mdx.ac.uk/id/eprint/28369

Actions (login required)

Edit Item Edit Item

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year