{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:30:32Z","timestamp":1753893032854,"version":"3.41.2"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["13N16242"],"award-info":[{"award-number":["13N16242"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Criminal investigation analysis involves processing large amounts of data, making manual analysis impractical. Artificial intelligence (AI)-driven information extraction systems can assist investigators in handling this data, leading to significant improvements in effectiveness and efficiency. However, the use of AI in criminal investigations also poses significant risks to individuals, requiring the integration of contestability into systems and processes. To meet this challenge, contestability requirements must be tailored to specific contexts. In this work, we analyzed and adapted existing requirements for criminal investigation analysis, focusing on the retrospective analysis of police reports. For this purpose, we introduced a novel information extraction pipeline based on three language modeling tasks, which we refer to as semantic modeling. Building on this concept, we evaluated contestability requirements and integrated them into our system. As a proof of concept, we developed an AI-driven information extraction system that incorporates contestability features and provides multiple functionalities for data analysis. Our findings highlight three key perspectives essential for contestability in AI-driven investigations: information provision, interactive controls, and quality assurance. This work contributes to the development of more transparent, accountable, and adaptable AI systems for law enforcement applications.<\/jats:p>","DOI":"10.3389\/frai.2025.1602998","type":"journal-article","created":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T05:29:14Z","timestamp":1751347754000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Contestable AI for criminal intelligence analysis: improving decision-making through semantic modeling and human oversight"],"prefix":"10.3389","volume":"8","author":[{"given":"Falk","family":"Maoro","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michaela","family":"Geierhos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/978-3-030-57977-7_12","article-title":"\u201cContestable black boxes,\u201d","author":"Aler Tubella","year":"2020","journal-title":"Rules and Reasoning"},{"key":"B2","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1007\/s11023-022-09611-z","article-title":"Contestable AI by design: towards a framework","volume":"33","author":"Alfrink","year":"2023","journal-title":"Minds Mach"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10506-021-09286-4","article-title":"A review of predictive policing from the perspective of fairness","volume":"30","author":"Alikhademi","year":"2022","journal-title":"Artif. Intellig. Law"},{"key":"B4","first-page":"2","article-title":"\u201cHuman intervention in automated decision-making: Toward the construction of contestable systems,\u201d","volume-title":"Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law, ICAIL '19","author":"Almada","year":"2019"},{"volume-title":"Machine Bias","year":"2016","author":"Angwin","key":"B5"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2101.12717","article-title":"Machine translation, sentiment analysis, text similarity, topic modelling, and tweets: understanding social media usage among police and gendarmerie organizations","author":"Ates","year":"2021","journal-title":"arXiv"},{"key":"B7","article-title":"\u201cLocal vs. global interpretability: a computational complexity perspective,\u201d","volume-title":"Forty-First International Conference on Machine Learning","author":"Bassan","year":"2024"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1058","DOI":"10.1111\/rego.12391","article-title":"The right to contest automated decisions under the General Data Protection Regulation: Beyond the so-called \u201cright to explanation\u201d","volume":"16","author":"Bayamlho\u011flu","year":"2022","journal-title":"Regul. Gov"},{"key":"B9","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1007\/978-3-030-17065-3_36","article-title":"\u201cAn automated system for criminal police reports analysis,\u201d","author":"Carnaz","year":"2020","journal-title":"Proceedings of the Tenth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2018)"},{"key":"B10","first-page":"494","article-title":"\u201cA review on relations extraction in police reports,\u201d","author":"Carnaz","year":"2019","journal-title":"New Knowledge in Information Systems and Technologies"},{"key":"B11","first-page":"6788","article-title":"\u201cGerman's next language model,\u201d","author":"Chan","year":"2020","journal-title":"Proceedings of the 28th International Conference on Computational Linguistics"},{"key":"B12","first-page":"315","article-title":"\u201cAutoXAI: a framework to automatically select the most adapted XAI solution,\u201d","author":"Cugny","year":"2022","journal-title":"Proceedings of the 31st ACM International Conference on Information"},{"key":"B13","first-page":"4171","article-title":"\u201cBERT: pre-training of deep bidirectional transformers for language understanding,\u201d","author":"Devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"key":"B14","doi-asserted-by":"publisher","first-page":"102162","DOI":"10.1016\/j.is.2022.102162","article-title":"A quantitative approach for the comparison of additive local explanation methods","volume":"114","author":"Doumard","year":"2023","journal-title":"Inf. Syst"},{"key":"B15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3407023.3407068","article-title":"\u201cSoK: exploring the state of the art and the future potential of artificial intelligence in digital forensic investigation,\u201d","volume-title":"Proceedings of the 15th International Conference on Availability, Reliability and Security, ARES '20","author":"Du","year":"2020"},{"key":"B16","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/j.procs.2024.05.101","article-title":"Artificial intelligence as an innovative element of support in policing","volume":"237","author":"Dubravova","year":"2024","journal-title":"Procedia Comput. Sci"},{"key":"B17","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1007\/s10506-022-09330-x","article-title":"Policing based on automatic facial recognition","volume":"31","author":"Guo","year":"2023","journal-title":"Artif. Intellig. Law"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1016\/j.procs.2020.03.357","article-title":"A clustering based hotspot identification approach for crime prediction","volume":"167","author":"Hajela","year":"2020","journal-title":"Procedia Comput. Sci"},{"key":"B19","first-page":"745","article-title":"\u201cMore data, more relations, more context and more openness: a review and outlook for relation extraction,\u201d","author":"Han","year":"2020","journal-title":"Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing"},{"key":"B20","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1007\/s43681-021-00054-3","article-title":"A framework to contest and justify algorithmic decisions","volume":"1","author":"Henin","year":"2021","journal-title":"AI Ethics"},{"key":"B21","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1145\/3064663.3064703","article-title":"\u201cDesigning contestability: interaction design, machine learning, and mental health,\u201d","volume-title":"Proceedings of the 2017 Conference on Designing Interactive Systems, DIS '17","author":"Hirsch","year":"2017"},{"key":"B22","first-page":"148","article-title":"\u201cFighting Back Algocracy: the need for new participatory approaches to technology assessment,\u201d","author":"Kariotis","year":"2020","journal-title":"Proceedings of the 16th Participatory Design Conference 2020"},{"key":"B23","first-page":"66","article-title":"\u201cSelection of XAI methods matters: evaluation of feature attribution methods for oculomotoric biometric identification,\u201d","volume-title":"Proceedings of The 1st Gaze Meets ML Workshop","author":"Krakowczyk","year":"2023"},{"key":"B24","doi-asserted-by":"crossref","first-page":"10154","DOI":"10.1145\/3664647.3681089","article-title":"\u201cFKA-Owl: advancing multimodal fake news detection through knowledge-augmented LVLMs,\u201d","volume-title":"Proceedings of the 32nd ACM International Conference on Multimedia, MM '24","author":"Liu","year":"2024"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.11692","article-title":"RoBERTa: a robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3449180","article-title":"Conceptualising contestability: perspectives on contesting algorithmic decisions","volume":"106","author":"Lyons","year":"2021","journal-title":"Proc. ACM Hum.-Comput. Interact"},{"key":"B27","article-title":"\u201cEfficient estimation of word representations in vector space,\u201d","author":"Mikolov","year":"2013","journal-title":"1st International Conference on Learning Representations, ICLR 2013"},{"key":"B28","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1075\/li.30.1.03nad","article-title":"A survey of named entity recognition and classification","volume":"30","author":"Nadeau","year":"2007","journal-title":"Lingvistic\u00e6 Investigationes"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-63438-X","volume-title":"Information Extraction A Multidisciplinary Approach to an Emerging Information Technology: International Summer School, SCIE-97 Frascati, Italy, July 14\u201318, 1997, volume 1299 of Lecture Notes in Computer Science","author":"Pazienza","year":"1997"},{"key":"B30","doi-asserted-by":"publisher","first-page":"101901","DOI":"10.1016\/j.artmed.2020.101901","article-title":"The four dimensions of contestable AI diagnostics - a patient-centric approach to explainable AI","volume":"107","author":"Ploug","year":"2020","journal-title":"Artif. Intell. Med"},{"key":"B31","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s00287-021-01332-4","article-title":"Predictive policing","volume":"44","author":"Povalej","year":"2021","journal-title":"Informatik Spektrum"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.16061","article-title":"Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation","author":"Powers","year":"2020","journal-title":"arXiv"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.1910.10683","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"B34","first-page":"82","article-title":"\u201cText chunking using transformation-based learning,\u201d","volume-title":"Third Workshop on Very Large Corpora","author":"Ramshaw","year":"1995"},{"key":"B35","article-title":"\u201cA maximum entropy model for part-of-speech tagging,\u201d","volume-title":"Conference on Empirical Methods in Natural Language Processing","author":"Ratnaparkhi","year":"1996"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2011.06993","article-title":"FLERT: document-level features for named entity recognition","author":"Schweter","year":"2021","journal-title":"arXiv"},{"key":"B37","doi-asserted-by":"publisher","first-page":"106092","DOI":"10.1016\/j.clsr.2024.106092","article-title":"Facial recognition technology in law enforcement: Regulating data analysis of another kind","volume":"56","author":"Simmler","year":"2025","journal-title":"Comp. Law Secur. Rev"},{"key":"B38","doi-asserted-by":"crossref","first-page":"142","DOI":"10.3115\/1119176.1119195","article-title":"\u201cIntroduction to the CoNLL-2003 shared task: language-independent named entity recognition,\u201d","volume-title":"Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003","author":"Tjong Kim Sang","year":"2003"},{"key":"B39","article-title":"\u201cAttention is all you need,\u201d","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Distributed Systems for System Architects, Volume 1","year":"2012","author":"Verissimo","key":"B40"},{"key":"B41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3699710","article-title":"Deepfake detection: a comprehensive survey from the reliability perspective","volume":"58","author":"Wang","year":"2024","journal-title":"ACM Comput. Surv"},{"key":"B42","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/1882471.1882478","article-title":"A brief survey on sequence classification","volume":"12","author":"Xing","year":"2010","journal-title":"SIGKDD Explor. Newsl"},{"key":"B43","doi-asserted-by":"crossref","first-page":"6442","DOI":"10.18653\/v1\/2020.emnlp-main.523","article-title":"\u201cLUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention,\u201d","author":"Yamada","year":"2020","journal-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"B44","doi-asserted-by":"crossref","first-page":"1596","DOI":"10.1145\/3630106.3658991","article-title":"\u201cEvidence of what, for whom? the socially contested role of algorithmic bias in a predictive policing tool,\u201d","volume-title":"Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, FAccT '24","author":"Ziosi","year":"2024"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1602998\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T05:29:23Z","timestamp":1751347763000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1602998\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":44,"alternative-id":["10.3389\/frai.2025.1602998"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1602998","relation":{},"ISSN":["2624-8212"],"issn-type":[{"type":"electronic","value":"2624-8212"}],"subject":[],"published":{"date-parts":[[2025,7,1]]},"article-number":"1602998"}}