一句话：通过混合方法实地评估犯罪关联 AI 决策支持工具，揭示分析师对 AI 预测的选择性信任与解释使用方式。
犯罪关联分析用于识别可能由同一人实施的一系列犯罪。实践中，分析师需在大型数据库中人工寻找行为与情境联系，耗时、认知负荷高，并可能反复接触令人不适的材料。为支持该工作，研究者与英国执法机构共同开发了 AI 决策支持工具。本文报告其工业评估：采用直接观察、眼动追踪、鼠标追踪与问卷的混合方法，考察分析师如何与 AI 预测及解释互动。结果显示，分析师选择性地使用 AI 预测，并频繁用非 AI 行为证据验证，体现部分信任与对既有实践的依赖；他们还关注模型特征，并提出改进解释呈现与工作流整合的机会。研究强调，高风险 AI 决策支持需整合解释与传统方法，并凸显现场评估的重要性。
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.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2607-08274,
title = {How Analysts Use AI in High-Stakes Crime Linkage: An Industrial Study},
author = {Jessica Woodhams and Amy Burrell and Wanyin Li and Fahim Ahmed and Matthew Tonkin and Jan Lemeire and Arkady Konovalov and Steven Frisson and Mark Webb and Sarah Galambos and Vesna Nowack and Dalal Alrajeh},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3805253}
}