Archives

Natural Language Processing: Improving Data Integrity of Police Recorded Crime

By Darren Cook, Research Fellow in Natural Language Processing at City, University of London

Did you know that police recorded crime data for England and Wales are not accredited by the UK’s Office for Statistics Regulation (OSR)? This decision, made by the OSR after an audit in 2014, was due to concerns about the reliability of the underlying data.

Various factors affect the quality of police-recorded data. Differences in IT systems, personnel decision-making, and a lack of knowledge-sharing all contribute to reduced quality and consistency. Poor data integrity leads to a lack of standardisation across police forces and an increase in inaccurate or missing entries. I recently spoke about this issue at the Behavioural and Social Sciences in Security (BASS) conference at the University of St. Andrews, Scotland.

Correcting missing values is no small feat. In a dataset of 18,000 police recorded domestic violence incidents, we found over 4,500 (25%) missing entries for a single variable. Let’s assume it takes 30 seconds to find the correct value for this variable – that’s 38 hours of effort – almost a full working week. Given that there could be as many as twenty additional variables, it would take over four months to populate all the missing values in our dataset. Expanding such effort across multiple police forces and for multiple types of crime highlights the inefficiency of human-effort in this endeavour.

In my talk, I outlined an automated solution to this problem using Natural Language Processing (NLP) and supervised machine learning (ML). NLP describes the processes and techniques used by machines to understand human language, and supervised ML describes how machines learn to predict an outcome based on previously seen examples. In this case, we sought to predict the relationship between the victim and offender – an important piece of demographic information vital to ensuring victim safety.

The proposed system would use a text-based crime ‘note’ completed by a police officer to classify the victim offender relationship as either ‘Ex-Partner”, “Partner”, or “Family” – in keeping with the distinction made by Women’s Aid. Crime notes are an often-overlooked source of information in police data, yet we found they consistently referenced the victim-offender relationship. The goal of our system, therefore, was to extract the salient information from the free-form crime notes and populate the corresponding missing value in our structured data fields.

Existing solutions based on keywords and syntax parsing are used by multiple UK police forces. While effective, they require manual effort to create, update, and maintain the dictionaries, and they don’t generalise well. Our supervised ML system, however, can be automatically updated and monitored to maintain accuracy.

When tested, our system achieved 80% accuracy, correctly labelling the relationship type in four out of five cases. In comparison, humans performed this task with approximately 82% accuracy – an arguably negligible difference. Moreover, once trained, our system could classify the entire test set (over 1,000 crime notes) in just sixteen seconds.

However, we noted some limitations, the biggest of which was a high linguistic overlap in crime notes between ‘Ex-Partner’ and ‘Partner’ that caused several misclassifications. We believe more advanced language models (i.e., word embeddings) will improve discrimination between these relationships.

We also discovered a potential prediction bias against minorities. Although victim ethnicity wasn’t included in our training setup, we observed reduced accuracy for Black or Asian victims. The source and extent of this bias are subjects of ongoing research.

Our findings highlight the promise of automated solutions but serve as a cautionary tale against assuming these systems can be applied carte blanche without careful consideration of their limitations. Several outstanding questions remain. Is a system with 80% accuracy good enough? Is it better to leave missing values rather than predict incorrect ones? Incorrectly identifying a perpetrator as a current partner rather than an ex-partner could significantly impact the victim’s safety. Additionally, a model biased against certain ethnicities risks overlooking the specific needs of minority groups.

The conference sparked lively and engaging conversation about many of these issues, as well as the role that automation can be play within the social sciences more broadly. A research article describing these results in full is the focus of ongoing work, and the presentation slides are available below as a download.

For further information please contact Darren at darren.cook@city.ac.uk or via LinkedIn @darrencook1986

Dr Darren Cook, An application of Natural Language Processing (NLP) to free-form Police crime notes – 1 download

D Cook_NLP and PoliceDownload

Photo by Markus Spiske on Unsplash

Differentiating risk: The association between relationship type and risk of repeat victimization of domestic abuse

Much of the literature on domestic abuse focuses on those in intimate partner relationships or ex-partners, however, in the UK the Home Office definition also includes those in familial relationships. The Domestic Abuse, Stalking, and Harassment and Honour-Based Violence Risk Assessment assumes homogeneous risk factors across all relationships.

This paper, Differentiating risk: The association between relationship type and risk of repeat victimization of domestic abuse, therefore examines the risk factors for repeat victimization of domestic abuse by relationship type between the victim and perpetrator in a UK police force.

Using police-recorded domestic abuse incident and crime data, a logistic regression model found that the most similar repeat victimization risk profiles for 14,519 victims were amongst partners and ex-partners, with both relationships demonstrating the greatest degree of gender asymmetry, compared with other familial relationships. Physical violence was the strongest predictor of repeat victimization and was a statistically significant predictor for ex-partners, partners, and all familial relationships. Coercive behaviour was also a significant predictor for all relationships apart from partners, but not at the same magnitude as physical abuse.

Recognizing the difference in risk by relationship type may assist the police in deciding the most appropriate response and interventions to reduce the risk of further harm. 

 For further information please see: https://academic.oup.com/policing/article/doi/10.1093/police/paae024/7641219?login=false

Or contact Ruth at ruth.weir@city.ac.uk  

Photo from licensed Adobe Stock library

Better utilisation of healthcare data to measure violence

Despite violence being recognised as a harm to health, it is not consistently or adequately captured in healthcare data systems. Administrative health records could be a valuable source for researching violence and understanding the needs of victims, but such datasets are currently underutilised for this purpose.

VISION researcher Dr Anastasia Fadeeva, with input from Dr Estela Capelas Barbosa, Professor Sally McManus and Public Health Wales’ Dr Alex Walker, examined violence indicators in emergency care, primary care, and linked healthcare datasets in the paper Using Primary Care and Emergency Department datasets for Researching Violence Victimisation in the UK.

Anastasia worked with Hospital Episode Statistics Accident and Emergency (HES A&E) and the Emergency Care Data Set (ECDS) while on secondment at the Department of Health and Social Care (DHSC), with helpful review provided by researchers in the department.

Among the datasets reviewed in the study, the South Wales Violence Surveillance dataset (police and emergency department data linked by Public Health Wales) had the most detail about violent acts and their contexts, while the Clinical Practice Research Datalink (CPRD) provided the more extensive range of socioeconomic factors about patients and extensive linkage with other datasets. Currently, detailed safeguarding information is routinely removed from the ECDS extracts provided to researchers, limiting its utility for violence research. In the HES A&E, only physical violence was consistently recorded.

Addressing these limitations and increasing awareness of the potential utility of health administrative datasets to violence-related research has the potential to provide insight into the health service needs of victims.

For further information please see: Social Sciences | Free Full-Text | Using Primary Care and Emergency Department Datasets for Researching Violence Victimisation in the UK: A Methodological Review of Four Sources (mdpi.com)

Or contact Dr Anastasia Fadeeva at anastasa.fadeeva@city.ac.uk

Photo from licensed Adobe Stock library

VISION Adolescent Domestic Abuse conference

This event is in the past.

If registered, please enter through the main entrance in the University Building, across from Northampton Square, a green space with a gazebo. There is also a silver sculpture in front of University Building.

Only those that registered will be able to enter the conference room.

To register please see: VISION and VASC Adolescent Domestic Abuse conference

The UK Prevention Research Partnership Violence, Health & Society (VISION) consortium and the Violence and Society Centre at City, University of London, are pleased to announce the Adolescent Domestic Abuse conference.

Thursday 18th April 2024, 10:00 – 17:00 followed by a reception 
Oliver Thompson Lecture Theatre (Tait Bldg), City, University of London, EC1B 0HB 

Adolescent domestic abuse, which includes physical, emotional, and/or sexual abuse that occurs between young people who are, or were, dating, is often overlooked in research, policy and practice. The current definition of domestic abuse leaves those aged under 16 in teenage relationships falling into the gap between child protection procedures and adult-focused domestic abuse policy. 

The conference brings together academics, practitioners, and policy makers to share existing research, policy and practice.

Registration is required and free. This is an in person conference only and catering will be provided. If you cannot attend but would like the slides, please contact the email listed below.

The programme: 

  • 9:30 – 10:00 Registration & refreshments 
  • 10:00 – 10:20 Welcome & setting the scene, Dr Ruth Weir, Violence and Society Centre, City, University of London and Katy Barrow-Grint, Assistant Chief Constable, Thames Valley Police
  • 10:20 – 10:40 Introductory Speaker, Louisa Rolfe OBE, Metropolitan Police and National Police Chief Council lead for Domestic Abuse
  • 10:40 – 11:00 Rapid evidence review on domestic abuse in teenage relationships, Flavia Lamarre, and Dr Ruth Weir, City, University of London
  • 11:00 – 11:30 Learning from the lived experience, SafeLives Changemakers
  • 11:30 – 12:00 Researching abuse within teenage relationships: A critique of a decade’s work and what we could do better, Professor Christine Barter, Co-Director of the Connect Centre for International Research on Interpersonal Violence and Harm, University of Central Lancashire 
  • 12:00 – 13:00 Lunch
  • 13:00 – 14:20 Panel 1: Teenage relationships and abuse: What the research says, chaired by Professor Sally McManus, Director of the Violence and Society Centre and Deputy Director of the VISION research project
  • Panel 1: Step up, Speak Out: Amplifying young people’s voices in understanding and responding to adolescent domestic abuse, Janelle Rabe, Centre for Research into Violence and Abuse, Durham University
  • Panel 1: ‘In practice it can be so much harder’: Young people’s approaches and experiences of supporting friends experiencing domestic abuse, Jen Daw and Sally Steadman South, SafeLives
  • Panel 1: Healthy relationships: children and young people attitudes and influences, Hannah Williams and Sarah Davidge, Women’s Aid
  • Panel 1: Intimate partner femicide against young women, Dr Shilan Caman, Karolinska Institutet, Sweden
  • 14:20 – 14:35 Break
  • 14:35 – 15:35 Panel 2: Sexual violence in teenage relationships, chaired by Katy Barrow-Grint, Thames Valley Police
  • Panel 2: “Always the rule that you can’t say no”: Adolescent women’s experiences of sexual violence in dating relationships – Dr Kirsty McGregor, Loughborough University 
  • Panel 2: Empowering Youth: Addressing Online Pornography and Adolescent Domestic Abuse – Insights from the CONSENT Project – Berta Vall, Elena Lloberas and Jaume Grané, Blanquerna, Barcelona, Spain and The European Network for Work with Perpetrators of Domestic Violence, Berlin, Germany
  • Panel 2: Image-Based Sexual Abuse as a Facet of Domestic Abuse in Young People’s Relationships – Dr Alishya Dhir, Durham University
  • 15:35 – 15:50 Break
  • 15:50 – 16:50 Panel 3: Specialist services and local government, chaired by Dr Olumide Adisa, University of Suffolk
  • Panel 3: The role and value of Early Intervention Workers in supporting children and young people aged 11–18 in a domestic abuse service context – Elaha Walizadeh and Leonor Capelier, Refuge 
  • Panel 3: Prevention, Identification, Intervention and Protection: Learning on teenage domestic abuse from a multi-agency model in the London Borough of Islington – Aisling Barker, Islington Borough Council
  • Panel 3: Tackling adolescent domestic abuse in Lambeth – Rose Parker, Erika Pavely, Ariana Markowitz, and Siofra Peeren, Lambeth Health Inequalities Research and Evaluation Network 
  • 16:50 – 17:00 Closing remarks and next steps
  • 17.00 – onwards Drinks reception, Conference attendees are invited to a drinks reception in the Oliver Thompson foyer

The abstracts

The abstracts and information on the poster presentations and stands are below for downloading.

ADA-abstracts-allDownload

For further information and any questions, please contact VISION at VISION_Management_Team@city.ac.uk

Photo by Tim Mossholder on Unsplash

Podcast on police and domestic violence publication

Hear VISION Senior Research Fellow, Ruth Weir, in conversation with Jackie Turton, University of Essex, as they discuss their recent publication, Policing Domestic Violence: Risk, Policy, and Practice, with Jules Pretty of The Louder than Words podcast series.

Ruth and Jackie collaborated with two serving police officers, Kate Barrow-Grint and Jacqueline Sebire, to write a book that improves police force understanding of the dynamics of how domestic abuse occurs, how best to respond to and investigate it, and, in the longer term, how to prevent it. 

It is a unique collaboration of real-life policing experience blended with the latest academic research and best practice to update some of the theoretical analysis and to highlight areas of good practice like what works and why.

To listen to the podcast please see: The Louder than Words podcast

Or contact Ruth at ruth.weir@city.ac.uk

Photo by Bruno Martins on Unsplash

Webinar: Police body-worn cameras & domestic violence responses

Dr Mary Iliadis, Deakin University

Wednesday, 9 August, 10:30 am – Noon, in-person and online

The VISION Consortium and the Violence and Society Centre at City, University of London, welcome Dr Mary Iliadis, Senior Lecturer in Criminology at Deakin University in Australia. She will present ‘The merits and risks of police body-worn cameras in domestic and family violence responses’ based on her recent publication in Policing and Society: An International Journal of Research and Policy.

Dr Iliadis will discuss the significant investment by Australian police agencies in the use of body-worn cameras (BWCs). Preliminary evidence suggests that when used in the context of domestic and family violence, BWC footage may strengthen evidential cases and prosecutions. There is, however, a paucity of research examining the merits of, and risks posed by the use of BWC footage in domestic and family violence incidents and legal proceedings.

Notably absent in much of the literature are the views and experiences of police officers who, as initial owners of BWC footage, are likely to affect how it is produced and interpreted. 

Her work is the first Australian study to examine how police officers, as users and operators of BWC technology, perceive the use of BWC footage in DFV-related civil and criminal legal proceedings in two Australian state jurisdictions: Western Australia and Queensland. The findings highlight the importance of exercising domain-specific, rather than a ‘one size fits all’ approach when it comes to understanding the benefits and limitations of BWC technology.

Join us in person at the Violence & Society Centre in the Rhind building on City campus from 10:30 am – noon or online. If in person, please note this seminar was originally in A01 College Building but is now in the Violence and Society Centre, 1st floor, Rhind Building.

Booking is required. Please email VISION_Management_Team@city.ac.uk and state whether you will be in person or online. A link will be emailed on the day to those attending online. Light refreshments will be served afterwards for those in person.

Policing Domestic Abuse hybrid seminar

Wednesday 1 March 2023, 10:30 am – Noon, in person and online

Hybrid event – Policing Domestic Abuse | Faculty of Law (ox.ac.uk)

Dr Ruth Weir, Senior Research Fellow with the UKPRP VISION consortium, will be presenting with her colleagues, Chief Superintendent Katy Barrow-Grint (Thames Valley Police), Professor Jackie Turton (University of Essex) and Dr Jackie Sebire (Institute of Criminology), on their book, Policing Domestic Abuse.

The book is dedicated to improving the practice of the policing of domestic abuse. Its objective is to help inform those working in policing about the dynamics of how domestic abuse occurs, how best to respond to and investigate it, and in the longer term how to prevent it. An effective investigation and the prosecution of offenders are considered, as well as an evaluation of the success of current treatment options. Policing domestic abuse can only be dealt with through an effective partnership response. The responsibilities of each agency and the statutory processes in place when policy is not adhered will also be outlined. The aim is to help shed light on the challenges of policing domestic violence and the links between academic research and best practice.

Understanding neighbourhood level predictors of domestic abuse and their variation over space

Reducing domestic abuse has become a priority for both local and national governments in the UK, with its substantial human, social, and economic costs. It is an interdisciplinary issue, but to date there has been no research in the UK that has focused on neighbourhood-level predictors of domestic abuse and their variation across space.

This article uses geographically weighted regression to model the predictors of police-reported domestic abuse in Essex. Readily available structural and cultural variables were found to predict the domestic abuse rate and the repeat victimisation rate at the lower super output area level and the model coefficients were all found to be non-stationary, indicating varying relationships across space. This research not only has important implications for victims’ well being, but also enables policy makers to gain a better understanding of the geography of victimisation, allowing targeted policy interventions and efficiently allocated resources.

For further information and the article, please see Using geographically weighted regression to explore neighborhood‐level predictors of domestic abuse in the UK – Weir – 2019 – Transactions in GIS – Wiley Online Library

Photo caption: Andrii Yalanskyi /Shutterstock.com

Book launch for new publication aimed at improving police responses to domestic abuse

How to respond and investigate domestic violence

On 15 November 2022, City, University of London hosted a book launch for Policing Domestic Violence, written by Katy Barrow Grint, Thames Valley Police; Dr Jacqueline Sebire, Cambridge University; Professor Jackie Turton, University of Essex; and Dr Ruth Weir, City, University of London. The event, held in The Pavilion, was attended by local police forces including the Metropolitan Police and Thames Valley Police as well as academics researching domestic violence. The keynote speakers were Louisa Rolfe, OBE, Assistant Commissioner of the Met, and Nicole Jacobs, the Domestic Abuse Commissioner.

The book, Policing Domestic Violence, is dedicated to improving the practice of the policing of domestic abuse. Its objective is to help inform those working in policing about the dynamics of how domestic abuse occurs, how best to respond to and investigate it, and in the longer term how to prevent it. Divided into thematic areas, the book uses recent research findings to update some of the theoretical analysis and to highlight areas of good practice: ‘what works and why’. An effective investigation and the prosecution of offenders are considered, as well as an evaluation of the success of current treatment options. Policing domestic abuse can only be dealt with through an effective partnership response. The responsibilities of each agency and the statutory processes in place when policy is not adhered to are outlined.

Written with the student and budding practitioner in mind, this book is filled with case studies, current research, reports, and media examples, as well as a variety of reflective questions and a glossary of key terms, to help shed light on the challenges of policing domestic violence and the links between academic research and best practice.

Photo caption: from left to right – Dr Ruth Weir, City University; Dr Jackie Turton, University of Essex; Nicole Jacobs, Domestic Abuse Commissioner; Louisa Rolfe, OBE, Assistant Commissioner at the Metropolitan Police; and Katy Barrow Grint, Thames Valley Police