In this paper, we demonstrate how insight seeking strategies and rules can be captured from analyst interactions with a question-answer system, as they perform an investigation. We present our analysis of an interactive investigation exercise undertaken by 14 experienced intelligence analysts. We propose that our approach to model the abstract higher order cognition involved in insight seeking provides a means to design intelligent systems that can reward and optimise potential lines of inquiry, ultimately creating the environment from which insights can be derived.
Fournier-VigerP.GomarizA.GuenicheT.SoltaniA.WuC.-W.TsengV. S. (2016). The SPMF Open-Source Data Mining Library Version 2. In Proceedings of the 19th European Conference on Principles of Data Mining and Knowledge Discovery (PKDD 2016) (pp. 36–40). Springer.
2.
GerberM.WongB. W.KodagodaN. (2016). How Analysts Think: Intuition, Leap of Faith and Insight. Proceedings of the Human Factors and Ergonomics Society Annual Meeting (pp. 173–177). Sage.
3.
HepenstalS.ZhangL. K.WongB. W. (2020). Pan: Conversational Agent for Criminal Investigations. Proceedings of the 25th International Conference on Intelligent User Interfaces Companion (Cagliari, Italy) (IUI ‘20) (pp. 134–135). Cagliari: ACM.
4.
HepenstalS.ZhangL.KodagodaN.WongB. W. (2020). Providing a foundation for interpretable autonomous agents through elicitation and modelling of criminal investigation pathways. In Proceedings of the 64th Human Factors and Ergonomics Society Annual Meeting. Sage.
5.
KleinG. (2011). A Naturalistic Study of Insight. Journal of Cognitive Engineering and Decision Making, 335–351.
6.
KleinG.JaroszA. (2011). A Naturalistic Study of Insight. Journal of Cognitive Engineering and Decision Making.
7.
KujalaT.SaariluomaP. (2018). Cognitive Mimetics for Designing Intelligent Technologies. Advances in Human-Computer Interaction.
