arXiv subjects

Amy Burrell

Publications and source records attributed to Amy Burrell.

3 recordsLinked to original sources

arXiv2026

How Analysts Use AI in High-Stakes Crime Linkage: An Industrial Study

Crime linkage analysis is used in many countries to identify series of offences that may have been committed by the same individual. In practice, specialist analysts manually search for behavioural and situational connections across large crime databases, an effort that is time-consuming, cognitively demanding, and can involve repeated exposure to disturbing material. To support this work, an Artificial Intelligence (AI)-enabled decision-support tool was co-developed with a UK law enforcement agency to assist analysts in identifying likely crime linkages. This paper reports an industrial evaluation of the crime-linkage tool. We conducted a mixed-methods usability study combining direct observation, eye-tracking, mouse-tracking, and surveys to examine how analysts engage with AI predictions and with the model features presented as explanations. Our findings show that analysts used the AI predictions selectively and frequently validated them against behavioural (non-AI) evidence, reflecting partial trust and an ongoing reliance on established analytical practices. We also found that analysts attended to the presented model features and valued their availability, while identifying opportunities to improve how explanations are presented and integrated into the workflow. Overall, our results highlight the need for AI-enabled decision-support tools to better integrate explanations and traditional analytical methods, and demonstrate the importance of in-situ evaluation for engineering usable and trustworthy AI in high-stakes settings.

cs.HC↗

arXiv2026

Data-Dependent Goal Modeling for ML-Enabled Law Enforcement Systems

Investigating serious crimes is inherently complex and resource-constrained. Law enforcement agencies (LEAs) grapple with overwhelming volumes of offender and incident data, making effective suspect identification difficult. Although machine learning (ML)-enabled systems have been explored to support LEAs, several have failed in practice. This highlights the need to align system behavior with stakeholder goals early in development, motivating the use of Goal-Oriented Requirements Engineering (GORE). This paper reports our experience applying the GORE framework KAOS to designing an ML-enabled system for identifying suspects in online child sexual abuse. We describe how KAOS supported early requirements elaboration, including goal refinement, object modeling, agent assignment, and operationalization. A key finding is the central role of data elicitation: data requirements constrain refinement choices and candidate agents while influencing how goals are linked, operationalized, and satisfied. Conversely, goal elaboration and agent assignment shape data quality expectations and collection needs. Our experience highlights the iterative, bidirectional dependencies between goals, data, and ML performance. We contribute a reference model for integrating GORE with data-driven system development, and identify gaps in KAOS, particularly the need for explicit support for data elicitation and quality management. These insights inform future extensions of KAOS and, more broadly, the application of formal GORE methods to ML-enabled systems for high-stakes societal contexts.

cs.CY↗

arXiv2025

Enhancing Binary Encoded Crime Linkage Analysis Using Siamese Network

Effective crime linkage analysis is crucial for identifying serial offenders and enhancing public safety. To address limitations of traditional crime linkage methods in handling high-dimensional, sparse, and heterogeneous data, we propose a Siamese Autoencoder framework that learns meaningful latent representations and uncovers correlations in complex crime data. Using data from the Violent Crime Linkage Analysis System (ViCLAS), maintained by the Serious Crime Analysis Section of the UK's National Crime Agency, our approach mitigates signal dilution in sparse feature spaces by integrating geographic-temporal features at the decoder stage. This design amplifies behavioral representations rather than allowing them to be overshadowed at the input level, yielding consistent improvements across multiple evaluation metrics. We further analyze how different domain-informed data reduction strategies influence model performance, providing practical guidance for preprocessing in crime linkage contexts. Our results show that advanced machine learning approaches can substantially enhance linkage accuracy, improving AUC by up to 9% over traditional methods while offering interpretable insights to support investigative decision-making.

cs.LG↗