Analytic provenance as constructs of behavioural markers for externalizing thinking processes in criminal intelligence analysis

Islam, Junayed, Wong, B. L. William and Xu, Kai (2018) Analytic provenance as constructs of behavioural markers for externalizing thinking processes in criminal intelligence analysis. In: Community-Oriented Policing and Technological Innovations. Leventakis, Georgios and Haberfeld, M. R., eds. SpringerBriefs in Criminology . Springer, pp. 95-105. ISBN 9783319892931

[img]
Preview
PDF - Published version (with publisher's formatting)
Available under License Creative Commons Attribution.

Download (327kB) | Preview

Abstract

Studying how analysts use interaction in visualization systems is an important part of evaluating how well these interactions support analysis needs, like generating insights or performing tasks. Analytic Provenance commonly known as interaction histories contains information about the sequence of choices that analysts make when exploring data or performing a task. This research work presents a compositional reductionist approach as a way of externalizing analyst’s thinking processes by using markers of analytical behaviour extracted from such interaction histories. Set of Behavioural Markers (BMs) have been identified through a workshop with domain experts and a systematic literature review to use them as cognitive attributes of imagination, insight, transparency, fluidity and rigour to enhance performance in criminal intelligence analysis. A low level semantic action sequence computation also has been proposed as a detection approach of identified BMs and found from computation that BMs can act as bridge between human cognition and computation through semantic interaction. This research work has addressed problems of existing qualitative experiments to extract these BMs through cognitive task analysis and found that the proposed computational technique can be a supplementary approach for validating experimental results.

Item Type: Book Section
Additional Information: Print ISBN: 978-3-319-89293-1. Online ISBN: 978-3-319-89294-8. Series Print ISSN: 2192-8533. Series Online ISSN: 2192-8541
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 24191
Useful Links:
Depositing User: Junayed Islam
Date Deposited: 30 Apr 2018 10:21
Last Modified: 04 Apr 2019 05:52
URI: https://eprints.mdx.ac.uk/id/eprint/24191

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