Developing conversational agents for use in criminal investigations

Journal article


Hepenstal, S., Zhang, L., Kodagoda N. and Wong B.L.W 2021. Developing conversational agents for use in criminal investigations. ACM Transactions on Interactive Intelligent Systems. 11 (3-4), pp. 1-35. https://doi.org/10.1145/3444369
AuthorsHepenstal, S., Zhang, L., Kodagoda N. and Wong B.L.W
Abstract

The adoption of artificial intelligence (AI) systems in environments that involve high risk and high consequence
decision making is severely hampered by critical design issues. These issues include system transparency
and brittleness, where transparency relates to (i) the explainability of results and (ii) the ability of a user to inspect and verify system goals and constraints, and brittleness (iii) the ability of a system to adapt to new user demands. Transparency is a particular concern for criminal intelligence analysis, where there are significant ethical and trust issues that arise when algorithmic and system processes are not adequately understood by a user. This prevents adoption of potentially useful technologies in policing environments.

In this paper, we present a novel approach to designing a conversational agent (CA) AI system for intelligence analysis that tackles these issues.We discuss the results and implications of three different studies; a Cognitive Task Analysis to understand analyst thinking when retrieving information in an investigation, Emergent Themes Analysis to understand the explanation needs of different system components, and an interactive experiment with a prototype conversational agent. Our prototype conversational agent, named Pan, demonstrates transparency provision and mitigates brittleness by evolving new CA intentions. We encode interactions with the CA with human factors principles for situation recognition and use interactive visual analytics to support analyst reasoning. Our approach enables complex AI systems, such as Pan, to be used in sensitive environments and our research has broader application than the use case discussed.

KeywordsExplainability; Criminal intelligence analysis; Conversational agents; Transparency
Year2021
JournalACM Transactions on Interactive Intelligent Systems
Journal citation11 (3-4), pp. 1-35
PublisherACM
ISSN2160-6455
Digital Object Identifier (DOI)https://doi.org/10.1145/3444369
Official URLhttps://dl.acm.org/doi/abs/10.1145/3444369
Publication dates
Online31 Aug 2021
Publication process dates
Accepted01 Dec 2020
Deposited03 Nov 2021
Accepted author manuscript
Output statusPublished
Permalink -

https://repository.canterbury.ac.uk/item/8z653/developing-conversational-agents-for-use-in-criminal-investigations

Download files


Accepted author manuscript
  • 110
    total views
  • 165
    total downloads
  • 2
    views this month
  • 3
    downloads this month

Export as

Related outputs

Investigating security issues (multilayer attacks) on IoT devices using machine learning
Al Sukhni, B., Manna, S., Dave, J. and Zhang, L. 2024. Investigating security issues (multilayer attacks) on IoT devices using machine learning.
Safeguarding IoMT: Semi-automated Intrusion Detection System (SAIDS) for detecting multilayer attacks
Al Sukhni, B., Manna, S., Dave, J. and Zhang, L. 2024. Safeguarding IoMT: Semi-automated Intrusion Detection System (SAIDS) for detecting multilayer attacks.
Exploring optimal set of features in machine learning for improving IoT multilayer security
Al Sukhni, B., Manna, S., Dave, J. and Zhang, Leishi 2023. Exploring optimal set of features in machine learning for improving IoT multilayer security. 2023 IEEE 9th World Forum on Internet of Things (WF-IoT). https://doi.org/10.1109/wf-iot58464.2023.10539376
A review of privacy-preserving federated learning, deep learning, and machine learning IIoT and IoTs solutions
Obarafor, Victor, Qi, Man and Zhang, L. 2023. A review of privacy-preserving federated learning, deep learning, and machine learning IIoT and IoTs solutions. in: 2023 8th IEEE International Conference on Signal and Image Processing (ICSIP) Wuxi, China IEEE. pp. 1074-1078
The impact of system transparency on analytical reasoning
Hepenstal, S., Zhang, L. and Wong, B. 2023. The impact of system transparency on analytical reasoning. in: CHI '23: CHI Conference on Human Factors in Computing Systems, Hamburg Germany, April 23 - 28, 2023 New York ACM.
The impact of system transparency on analytical reasoning
Hepenstal, S., Zhang, L. and Wong, B.L.W. 2023. The impact of system transparency on analytical reasoning.
Machine learning-based solutions for securing IoT systems against multilayer attacks
Al Sukhni, B., Manna, S., Dave, J. and Zhang, L. 2022. Machine learning-based solutions for securing IoT systems against multilayer attacks. in: Singh Tomar, R., Verma, S., Kumar Chaurasia, B., Singh, V., Abawajy, J. H., Akashe, S., Hsiung, Pao-Ann and Prasad, R. (ed.) Communication, Networks and Computing Third International Conference, CNC 2022, Gwalior, India, December 8–10, 2022, Proceedings, Part I Cham Springer. pp. 140-153
Investigating the security issues of multi-layer IoMT attacks using machine learning techniques
Al Sukhni, B., Manna, S., Dave, J. and Zhang, L. 2022. Investigating the security issues of multi-layer IoMT attacks using machine learning techniques.
Designing a system to mimic expert cognition: An initial prototype
Hepenstal, Sam, Zhang, Leishi and William Wong, B. L. 2022. Designing a system to mimic expert cognition: An initial prototype. Proceedings of the Human Factors and Ergonomics Society Annual Meeting. 66 (1), pp. 2057-2061. https://doi.org/10.1177/1071181322661092
An analysis of expertise in intelligence analysis to support the design of human-centered artificial intelligence
Hepenstal, S., Zhang, L. and Wong, BL William 2021. An analysis of expertise in intelligence analysis to support the design of human-centered artificial intelligence. https://doi.org/10.1109/SMC52423.2021.9659095
Automated identification of insight seeking behaviours, strategies and rules: a preliminary study
Hepenstal, S., Zhang, L. and Wong, BL William 2021. Automated identification of insight seeking behaviours, strategies and rules: a preliminary study. Sage Journals: Proceedings of the Human Factors and Ergonomics Society Annual Meeting . (65), pp. 1269-1273. https://doi.org/https://doi.org/10.1177/1071181321651348
A granular computing approach to provide transparency of intelligent systems for criminal investigations
Zhang, L. 2021. A granular computing approach to provide transparency of intelligent systems for criminal investigations. in: Pedrycz, W. and Chen, S.-M. (ed.) Interpretable Artificial Intelligence: A Perspective of Granular Computing Cham Springer.