{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T23:11:09Z","timestamp":1783120269522,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The Research Council of Norway","award":["333898"],"award-info":[{"award-number":["333898"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1145\/3712716.3712719","type":"proceedings-article","created":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:10:13Z","timestamp":1743145813000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Fast Synthetic Data Generation for Case-Specific Entity Extraction in Criminal Investigations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9382-1268","authenticated-orcid":false,"given":"Mads","family":"Skipanes","sequence":"first","affiliation":[{"name":"The National Criminal Investigation Service (Kripos), Oslo, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8710-4653","authenticated-orcid":false,"given":"Nardiena","family":"Pratama","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1363-9615","authenticated-orcid":false,"given":"Kyle","family":"Porter","sequence":"additional","affiliation":[{"name":"Department of Information Security and Communication Technology, The Norwegian University of Science and Technology, Gjovik, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7311-3693","authenticated-orcid":false,"given":"Gianluca","family":"Demartini","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","unstructured":"Rabeah Al-Zaidy Benjamin\u00a0C.M. Fung Amr\u00a0M. Youssef and Francis Fortin. 2012. Mining criminal networks from unstructured text documents. Digital Investigation 8 3-4 (Feb. 2012) 147\u2013160. 10.1016\/j.diin.2011.12.001","DOI":"10.1016\/j.diin.2011.12.001"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/SMDS53860.2021.00031"},{"key":"e_1_3_3_2_4_2","volume-title":"Named entity recognition in the legal domain for ontology population","author":"Bruckschen M","year":"2010","unstructured":"M Bruckschen, Caio Northfleet, D Silva, Paulo Bridi, Roger Granada, Renata Vieira, Prasad Rao, and Tomas Sander. 2010. Named entity recognition in the legal domain for ontology population."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Eoghan Casey Sean Barnum Ryan Griffith Jonathan Snyder Harm van Beek and Alex Nelson. 2017. Advancing coordinated cyber-investigations and tool interoperability using a community developed specification language. Digital investigation 22 (2017) 14\u201345.","DOI":"10.1016\/j.diin.2017.08.002"},{"key":"e_1_3_3_2_6_2","unstructured":"Michael Chau Jennifer\u00a0J Xu and Hsinchun Chen. 2002. Extracting Meaningful Entities from Police Narrative Reports. (2002) 5."},{"key":"e_1_3_3_2_7_2","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. http:\/\/arxiv.org\/abs\/1810.04805 arXiv:https:\/\/arXiv.org\/abs\/1810.04805 [cs]."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Alaa El-Halees and Nael Elyezjy. 2015. Investigating Crimes using Text Mining and Network Analysis. International Journal of Computer Applications 126 (Sept. 2015) 19\u201325. 10.5120\/ijca2015906134","DOI":"10.5120\/ijca2015906134"},{"key":"e_1_3_3_2_9_2","first-page":"58","volume-title":"LegalAIIA@ ICAIL","author":"Henseler Hans","year":"2023","unstructured":"Hans Henseler and Harm van Beek. 2023. ChatGPT as a Copilot for Investigating Digital Evidence.. In LegalAIIA@ ICAIL. 58\u201369."},{"key":"e_1_3_3_2_10_2","first-page":"4597","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Hvingelby Rasmus","year":"2020","unstructured":"Rasmus Hvingelby, Amalie\u00a0Brogaard Pauli, Maria Barrett, Christina Rosted, Lasse\u00a0Malm Lidegaard, and Anders S\u00f8gaard. 2020. DaNE: A Named Entity Resource for Danish. In Proceedings of the Twelfth Language Resources and Evaluation Conference, Nicoletta Calzolari, Fr\u00e9d\u00e9ric B\u00e9chet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, H\u00e9l\u00e8ne Mazo, Asuncion Moreno, Jan Odijk, and Stelios Piperidis (Eds.). European Language Resources Association, Marseille, France, 4597\u20134604. https:\/\/aclanthology.org\/2020.lrec-1.565\/"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780199259427.001.0001","volume-title":"Investigating murder : detective work and the police response to criminal homicide","author":"Innes Martin","year":"2003","unstructured":"Martin Innes. 2003. Investigating murder : detective work and the police response to criminal homicide. Oxford University Press, Oxford ; New York."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Farkhund Iqbal Benjamin\u00a0CM Fung Mourad Debbabi Rabia Batool and Andrew Marrington. 2019. Wordnet-based criminal networks mining for cybercrime investigation. Ieee Access 7 (2019) 22740\u201322755.","DOI":"10.1109\/ACCESS.2019.2891694"},{"key":"e_1_3_3_2_13_2","unstructured":"Fredrik J\u00f8rgensen Tobias Aasmoe Anne-Stine\u00a0Ruud Husev\u00e5g Lilja \u00d8vrelid and Erik Velldal. 2020. NorNE: Annotating Named Entities for Norwegian. arxiv:https:\/\/arXiv.org\/abs\/1911.12146\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1911.12146"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Mayank Kejriwal Pedro Szekely and Craig Knoblock. 2018. Investigative Knowledge Discovery for Combating Illicit Activities. IEEE Intelligent Systems 33 1 (Jan. 2018) 53\u201363. 10.1109\/MIS.2018.111144556Conference Name: IEEE Intelligent Systems.","DOI":"10.1109\/MIS.2018.111144556"},{"key":"e_1_3_3_2_15_2","first-page":"20","volume-title":"Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)","author":"Kummervold Per\u00a0E","year":"2021","unstructured":"Per\u00a0E Kummervold, Javier De\u00a0la Rosa, Freddy Wetjen, and Svein\u00a0Arne Brygfjeld. 2021. Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model. In Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa). Link\u00f6ping University Electronic Press, Sweden, Reykjavik, Iceland (Online), 20\u201329. https:\/\/aclanthology.org\/2021.nodalida-main.3"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Al Louis and Andries\u00a0P Engelbrecht. 2011. Unsupervised discovery of relations for analysis of textual data. digital investigation 7 3-4 (2011) 154\u2013171.","DOI":"10.1016\/j.diin.2010.08.004"},{"key":"e_1_3_3_2_17_2","unstructured":"Alf\u00a0Bernt Nissen. 2018. Informasjonsbehandling i store etterforskningssaker. (2018)."},{"key":"e_1_3_3_2_18_2","unstructured":"Alf\u00a0Bernt Nissen. 2019. Politiets system for Operativ kriminalanalyse."},{"key":"e_1_3_3_2_19_2","unstructured":"Homicide Working\u00a0Group NPCC. 2021. Major Incident Room Standardised Administrative Procedures (MIRSAP 2021). (2021)."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Vitor Oliveira Gabriel Nogueira Thiago Faleiros and Ricardo Marcacini. 2024. Combining prompt-based language models and weak supervision for labeling named entity recognition on legal documents. Artificial Intelligence and Law (2024) 1\u201321.","DOI":"10.1007\/s10506-023-09388-1"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1178"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Yerin Park Ro\u00a0Seop Park and Hansoo Kim. 2024. Key Information Extraction for Crime Investigation by Hybrid Classification Model. Electronics 13 8 (2024) 1525.","DOI":"10.3390\/electronics13081525"},{"key":"e_1_3_3_2_23_2","unstructured":"Mark Pollitt. 2013. The hermeneutics of the hard drive: Using narratology natural language processing and knowledge management to improve the effectiveness of the digital forensic process. (2013)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Fillipe\u00a0Barros Rodrigues William\u00a0Ferreira Giozza Robson de Oliveira\u00a0Albuquerque and Luis\u00a0Javier Garc\u00eda\u00a0Villalba. 2022. Natural Language Processing Applied to Forensics Information Extraction With Transformers and Graph Visualization. IEEE Transactions on Computational Social Systems (2022) 1\u201317. 10.1109\/TCSS.2022.3159677Conference Name: IEEE Transactions on Computational Social Systems.","DOI":"10.1109\/TCSS.2022.3159677"},{"key":"e_1_3_3_2_25_2","unstructured":"Marijn Schraagen Matthieu Brinkhuis Floris Bex M\u00a0P Schraagen M\u00a0J\u00a0S Brinkhuis and F\u00a0J Bex. 2017. Evaluation of Named Entity Recognition in Dutch online criminal complaints. (2017)."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Mads Skipanes Katrin Franke Gianluca Demartini and Alf\u00a0Bernt Nissen. 2025. Information Analysis in Criminal Investigations: Methods Challenges and Computational Opportunities Processing Unstructured Text. Policing: A journal of Policy and Practise. (2025).","DOI":"10.1093\/police\/paaf005"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Mads Skipanes Tollef\u00a0Emil J\u00f8orgensen and Katrin Franke. 2023. Advancing Knowledge Discoveries in Criminal Investigations with Semantic Textual Similarity. (2023).","DOI":"10.3233\/FAIA230973"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-12778-1_3"},{"key":"e_1_3_3_2_29_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_30_2","unstructured":"Xinyu Wang Yong Jiang Nguyen Bach Tao Wang Zhongqiang Huang Fei Huang and Kewei Tu. 2020. Automated concatenation of embeddings for structured prediction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.05006 (2020)."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Xintao Xing and Peng Chen. 2024. Entity Extraction of Key Elements in 110 Police Reports Based on Large Language Models. Applied Sciences 14 17 (2024) 7819.","DOI":"10.3390\/app14177819"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24123-4_4"},{"key":"e_1_3_3_2_33_2","unstructured":"Anne\u00a0Mosvold \u00d8rke. 2023. Giving the Police a Head Start: Norwegian Named Entity Recognition Dataset and Model Development for Investigative Purposes. (2023)."}],"event":{"name":"DFDS 2025: Digital Forensics Doctoral Symposium","location":"Brno Czech Republic","acronym":"DFDS 2025"},"container-title":["Proceedings of the Digital Forensics Doctoral Symposium"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712716.3712719","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712716.3712719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:09Z","timestamp":1750295889000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712716.3712719"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":32,"alternative-id":["10.1145\/3712716.3712719","10.1145\/3712716"],"URL":"https:\/\/doi.org\/10.1145\/3712716.3712719","relation":{},"subject":[],"published":{"date-parts":[[2025,4]]},"assertion":[{"value":"2025-04-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}