Police reports made following attendance at various events (e.g., crashes, domestic violence, theft) often contain rich contextual details including indicators of mental health issues or abuse types, and persons/entities involved and their relationships, which are not typically captured in structured administrative data, interviews or official statistics. However, the sheer volume of information along with strict data access protocols render manual analysis impractical. Computational text analysis methods offer a feasible and effective approach to automatically process this underutilized data source. This article is an overview of studies using computational text analysis (e.g., text mining, natural language processing (NLP)), on unstructured police data, serving as a guide for researchers interested in employing similar methodologies. This scoping review was conducted in accordance with the PRISMA-SCR guidelines, following the two screening processes (title/abstract and full text screening) and the development of a pre-defined protocol. A search was conducted across seven electronic databases (ProQuest, IEEE Xplore, Scopus, PubMed, Web of Science, Criminal Justice Abstracts, Google Scholar) covering the past 20 years. A total of 5426 records were identified. After removing duplicate entries and screening titles/abstracts and full-text publications, 61 studies met the inclusion criteria. Included studies were published between 2004 and 2024, with most from the United States, Australia and the Netherlands. Most studies used opensource tools: Bidirectional Encoder Representations from Transformers (BERT), natural language tool kit (NLTK), scikit-learn, or General Architecture for Text Engineering (GATE) to analyze unstructured police data. Our review indicates applications of computational text analysis on unstructured police data have moderate to high performance. Common limitations included variable data quality, with reliability depending on the level of detail provided by the police report’s author, and failure to report ethical implications or methodological limitations. Computational text analysis can extract key information from unstructured police data. However, future research should clearly report ethics approvals and implications, and methodological limitations. Establishing a structured data-sharing framework between law enforcement and researchers is also crucial to facilitate access and support high quality, impactful research in this field.

Connected and Autonomous Vehicles (CAVs) integrate advanced communication and autonomous driving technologies, enabling them to operate independently or with minimal human intervention. Despite the anticipated benefits for transportation, CAVs could be vulnerable to a wide variety of crimes unless security and crime prevention measures are proactively integrated into the technologies enabling their operation. To understand the potential crime threats, an extensive scoping review was conducted, covering incidents reported in the news and media, along with academic articles from crime and cybersecurity research. A total of 70 news articles related to crime incidents were identified, along with 12 academic articles on crimes. In addition, the findings from 35 survey papers addressing security attacks against CAVs, along with 29 additional papers covering security attacks not addressed in those surveys were synthesised. A total of 22 crime threats were identified. A 2-day workshop with experts was then held to present the findings from the review, conduct a crime scenario development exercise to identify any crime threats that were not identified in the review, and to assess the identified crimes. During the workshop, experts generated 6 new crime scenarios, bringing the total to 28 crime threats. To identify and prioritise high-risk crimes for future work, the experts were then asked to rate the threats based on their anticipated harm, achievability, frequency, and defeat-ability. The crime threats with the highest risk ratings included illegal transportation, vehicle theft, vehicle part theft, ransom for financial gain, and vandalism. The implications of our findings for research, policy and practice are discussed.

Weather variables, like temperature and precipitation, have long been established as predictors of criminal behavior. So too have researchers established the importance of controlling for potentially criminogenic places when predicting when and where crimes will occur at micro-level units of analysis. The current study examines the role that temperature and precipitation play, along with places, in the odds of street robbery occurrence on street blocks in Cincinnati, Ohio. Using multilevel modeling, with days clustered within street blocks, our results showed that temperature, but not precipitation, predicted increased odds of street robbery occurrence, even after controlling for the presence of potentially criminogenic places. We conclude that research should continue to examine these important relationships, specifically how weather impacts the role of places in the formation of criminal opportunities.

BackgroundThis systematic review explores the impact of deepfakes on the criminal justice system. Deepfakes, a sophisticated form of AI-generated synthetic media, have raised concerns due to their potential to compromise the integrity of evidence and judicial processes. The review aims to assess the extent of this threat, guided by a research question: (1) What threats do deepfakes pose to the criminal justice system?MethodsThe review was conducted using databases such as Web of Science, ProQuest, Scopus, and Google Scholar, focusing on publications from 2021 to 2022. Search terms were optimised for sensitivity and specificity, and articles were chosen based on criteria including relevance to deepfake threats and deepfake detection research. The methodology included rigorous screening processes using tools like Zotero and Rayyan.ai, with an emphasis on inter-rater reliability to ensure objective selection of studies.ResultsThe search initially identified 1355 articles, with 1200 articles screened for eligibility after duplicates were removed. For the threat of deepfakes to the criminal justice system, 110 studies were selected for full-text review, and 44 were included in the final analysis. Key findings include identification of primary crime categories linked to deepfakes, such as pornography, fraud, and information manipulation, alongside challenges like trust erosion in institutions and evidence falsification issues.ConclusionsDeepfakes significantly threaten the criminal justice system, highlighting the necessity for advanced detection methods. These findings underscore the importance of continued research and development in deepfake detection technologies and strategies for legal safeguards and broader implications on policy, national security, and democratic processes.

Recently, Succar and Porfiri (Nature Cities 1(3):216–224, 2024) reported sublinear scaling for firearm ownership in the United States. Their analysis hinted at a causal role of prevalence of homicides and firearm accessibility on firearm ownership, supporting self-protection as a driver of firearm ownership. In this study, we propose a microscopic, individual-level model to explain these macroscopic, city-level findings. In the model, individuals dwell in a city and buy a gun if they experience a violent interaction and know a dealer. We examine the model from a network science perspective and show the emergence of sublinear scaling with an exponent matching empirical observations. Beyond scaling, the model provides accurate predictions of city rankings in terms of firearm ownership, underscoring the explanatory power of the self-protection theory.

Victims’ willingness to call the police facilitates access to the justice system and potential resources. Research shows a decline in police notification in the United States in recent decades, but the research has not assessed variation in trends across different racial/ethnic groups and different racial-immigration contexts. This study uses the National Crime Victimization Survey (NCVS) data from 52 metropolitan areas in the United States from 2000 to 2015 to investigate how victims across racial/ethnic groups vary in the likelihood of crime reporting based on geographic context. The results show that Black, Latino, and Asian victims’ crime-reporting behavior is influenced by the racial/ethnic and immigrant composition of the metropolitan areas. While the likelihood of police notification between racial/ethnic minorities and Whites is often similar when averaged across areas, minority victims in areas with higher percentages of Black or immigrant residents show a lower likelihood of crime reporting than their White counterparts. The higher percentage of immigrants is also associated with a steeper decline in the reporting of property crimes. These findings demonstrate the context-dependent nature of crime reporting. They help explain mixed evidence on the associations of race/ethnicity with police notification. To understand the crime-reporting behavior of victims, especially those who are racially marginalized, more attention to racial-immigration contexts is needed.

In this article (Trajtenberg et al., 2024) , the author name G. Breetzke was incorrectly written as G. Breeztke.