A team of researchers from the University of Maryland College Park and the University of Maryland Baltimore have received an MPower grant to support their project, “Comparing Firearm Violence from Trauma Units and Police,” which will analyze police data and shock trauma data in Baltimore to integrate public health and public safety knowledge and better understand the overlap between gun violence victims and offenders.

The project is co-led by principal investigators Gary LaFree, Professor and Founding Director of the Maryland Crime Research and Innovation Center (MCRIC) on the University of Maryland College Park campus, and Kyla Liggett-Creel, Clinical Assistant Professor in the School of Social Work on the University of Maryland Baltimore campus. The research team also includes Joseph Richardson, the Joel and Kim Feller Professor of African American Studies and Anthropology and MPower Professor; Corey Shdaimah, Professor in the School of Social Work at Baltimore; Kiminori Nakamura, Research Professor in the Department of Criminology and Criminal Justice at College Park; Paul Thurman, Nurse Scientist in Trauma and Critical Care at the University of Maryland Medical Center in Baltimore; and graduate research assistant, data analyst, and Ph.D. candidate Meghan Kozlowski-Serra.

The purpose of the proposed research is to better understand trends and community perceptions of gun violence by using a collaborative, community-based approach to identify modifiable risk factors for violence prevention.

While gun violence and its sequelae are the leading cause of death and disability among young males aged 18-34, prior research has been constrained by outdated conceptions of gun violence as a public health or a public safety problem. The latter has resulted in a research literature on gun violence divided into separate silos for studies of people who have committed gun violence and those who have survived gun violence.  The need for a better understanding of gun violence is especially acute in urban areas like Baltimore, which has experienced more than 300 homicides per year for the past five years, most of them gun-related. 

The researchers intend to leverage their data analysis and increased understanding to help develop strategies for: early intervention, gun violence reduction through early warning systems, criminal justice policy recommendations, and positive health outcomes, including reductions in early mortality, increased life expectancy, and decreased chronic disability associated with gun violence.

Researchers from the Maryland Crime Research and Innovation Center (MCRIC) at the University of Maryland launched a research study to increase understanding of pretrial outcomes in Maryland. Supported by a grant from the Governor’s Office of Crime Prevention, Youth, and Victim Services, project findings may help inform jurisdictions’ decision making and efforts to effectively reduce the local detention population while protecting public safety.

Bail is increasingly being recognized as an important focal point for criminal justice reform. The majority of individuals detained pretrial are accused of low-level, nonviolent offenses and pose little threat to public safety. The costs of detaining individuals pretrial are myriad, costing both governments and families upwards of $13.6 billion per year. Information is needed to support efforts in Maryland to effectively reduce the local detention population while protecting public safety.

The research team, which includes Bianca Bersani, Bryan Johnson, Zubin Jelveh, Kiminori Nakamura, and Shuvra Bhattacharyya, will analyze routine patterns of pretrial release in Maryland, including elements such as: overall rates of pretrial detention, average bail amounts, the proportion of defendants held on low cash bail, the proportion of defendants held without bail, and recidivism patterns by pretrial status.

The team will also investigate the use of publicly available court data to help inform decision making pertaining to pre-trial detention and bail. In particular, the team will investigate the application and optimization of machine learning algorithms for pre-trial analysis, utilizing novel machine learning methods that provide risk assessment for sentencing decisions.

A University of Maryland (UMD) research team affiliated with the Maryland Crime Research and Innovation Center (MCRIC) presented on a predictive analytics project focused on community safety and public health to a group of over 40 academic, health department, law enforcement, and public safety personnel at Salisbury University on August 24.

The main objective of the project is to increase the availability of data-driven predictive analytics that offer local officials an additional set of tools that can supplement and enhance existing proactive strategies to improve community health and public safety. The researchers are incorporating stakeholder feedback, testing predictive models, and developing a prototype software program called Computer Aided Tools & Applications Leading & Inspiring Community Safety (CATALICS), which they plan to make available for use as a pilot tool for practitioners, direct service providers, and community health and public safety personnel in the future.

The partnership between the City of Salisbury and the UMD team, comprised of Research Professor Kiminori Nakamura (Criminology and Criminal Justice), Professor Shuvra Bhattacharyya (Electrical and Computer Engineering and Institute for Advanced Computer Studies), Professor Rod Brunson (Criminology and Criminal Justice), and Yujunrong Ma, a graduate student in Electrical and Computer Engineering, was previously awarded an Edward Byrne Memorial Justice Assistance Grant (BJAG) from the Maryland Governor’s Office of Crime Prevention, Youth, and Victim Services (GOCPYVS) that has supported the work.  

Over the course of the project, the UMD team has engaged in data collection, research, and analysis to assist with the development of the prototype software package. The team is working to incorporate data on community health and safety concerns, such as drug overdoses and incidents of crime. The project will further incorporate various data sources for geographic and place-based features, as well as other types of data to improve the versatility and usefulness of the application.

The UMD team is working closely with Salisbury partners to help create an innovative, customized tool, prioritizing transparency with respect to the software application development. The team is also committed to fairness and equity in the development of the software, with the ultimate goal of improving public safety for all community members.

“Our approach differs from other predictive analytic strategies by incorporating stakeholder feedback, resulting in a more nuanced and carefully considered product that supports the unique community it is intended for,” said Nakamura.

The UMD researchers will continue to develop the software over the next year and intend to expand this collaborative project to include other partners and locations across Maryland.

According to lead investigator, Dr. Zubin Jelveh, there is still a gap in understanding how decisions are made about who should be detained.

The ability to jail individuals after they have been arrested — but before they have been convicted of a crime — is one of the most consequential decisions made by criminal court judges. In many jurisdictions in the United States, that decision hinges on whether a judge believes that a defendant is at high risk of committing a future crime. Getting the assessment wrong means that people who pose no public safety risk are mistakenly detained, which research shows can lead to future job loss, and even increase the chance that they will be rearrested in the future. While bail and pretrial detention are focal points for criminal justice reform in Maryland and across the country, there is still a substantial gap in understanding how and why decisions are made about who should be detained. 

To help increase the evidence base around this critical decision-point, the Maryland Governor’s Office of Crime Prevention, Youth, & Victim Services (GOCPYVS) awarded a team of University of Maryland researchers from the Maryland Crime Research and Innovation Center (MCRIC) a $313,000 grant to study how pretrial outcomes vary across Maryland jurisdictions. 

One of the primary reasons for pretrial detention is to increase community safety. However, many detained individuals have very low levels of risk of offending in the community while other predictably riskier individuals end up being released. In other words, it appears that judges are frequently making detention decisions that are not aligned with risk. For example, a 2017 study of pretrial decision-making in New York City found that a prediction algorithm could help cut the number of jailed individuals by nearly 50% without increasing crime rates. In fact, a number of jurisdictions have begun to use prediction algorithms to aid judges and other court actors in their assessment of risk. These algorithms work by using information on a defendant’s prior convictions, sentences, and current case information to generate an estimate of the chance that the defendant will be re-arrested during the duration of the trial. 

Unfortunately, the evidence on the real-world effectiveness of these tools is mixed. A study by researchers at University of Virginia and Texas A&M found that the introduction of a pretrial risk algorithm in Virginia did not lead to a reduction in crime. There is also a growing backlash against the usage of algorithms in these high-stakes situations. Voters in California voted against a bail reform referendum that would have introduced a prediction algorithm to aid in pretrial decisions made by judges.  

While this research points to the promises and pitfalls of the use of algorithms to help reduce crimes rates as well as the burden of false incarceration on marginalized populations, there is still much to learn, says lead investigator on the Maryland grant, Zubin Jelveh, Assistant Professor at the College of Information Studies (INFO College) and the Department of Criminology and Criminal Justice (CCJS) at the University of Maryland.

“Even though there is more and more research on pretrial decision-making, very little of it has focused on Maryland. On-the-ground context is so critical to understanding how complex systems like a court actually work, so it’s not obvious at all that the findings from other jurisdictions will apply to Maryland,” said Jelveh. “I see the long-term value of this project as not only providing new insights into decision-making, but also providing a test-bed for replicating prior findings in Maryland — all with the aim of improving policy, practice, and outcomes for the residents of Maryland.”

The MCRIC project draws on expertise from CCJS and the INFO College to provide important data necessary to understand the impact of past reforms in the state, such as the implementation of pretrial risk assessments in individual counties, and the potential for future reforms, such as a statewide bail reform effort. Building on prior work focusing on Baltimore City and Prince George’s County, the research team will first construct a large, linked dataset of criminal cases across the state of Maryland that spans more than a decade. This dataset will enable the research team to track cases from the initial hearing to final disposition. Drawing on methods from machine learning, criminology, and applied microeconomics, the team will then study the extent to which pretrial risk in Maryland is actually predictable, as well as the level of alignment between those risk predictions and decisions made by the court. 

“We are excited to have the opportunity to continue our partnership with the Governor’s Office on this important research to better inform jurisdictions across Maryland about pretrial decision-making,” said MCRIC Director Dr. Bianca Bersani. “This project is innovative in its use of a multijurisdictional approach examining practices not only within localities but also across jurisdictions such as between urban and rural areas. Understanding the pretrial process will help localities make more informed and effective decisions about pretrial release, reducing the local detention population while maintaining public safety.”

This article by Laurie Robinson was originally published on the College of Information Studies' website.

Violence Diffusion Prediction via Deep Learning

Kunpeng Zhang, Assistant Professor
Robert H. Smith School of Business

This project seeks to reduce or prevent violent crimes by using large-scale data collection from Twitter and a methodology called Recurrent Cascades Convolutional Networks (CasCN) to monitor, predict, and visualize violent cascades in a given area. Using user-generated data from Twitter, this research could help proactively offer information for law enforcement policies regarding violence.

The research implements real-time social media monitoring to dynamically predict the cascade size of a certain violent topic at a specific geographical area (e.g., if a robbery happened in College Park today, how many residents in this area will pay attention to it for the next three days?), in addition to standard reporting. The research leverages long short-term memory (LSTM) and graph convolutional network (GCN) to predict the future size of a given cascade.

Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example. Deep learning is used in technologies such as autonomous cars and voice-controlled devices. Using a deep-learning framework, the researcher is modeling the structural and temporal characteristics of violence, as well as the features. The algorithm is being implemented and evaluated using Python and Pytorch.

Next steps include using existing data to test and val

Stop the Addiction Fatality Epidemic (SAFE) Project Treatment Locator Application

Stephanie Weaver, Jeff Horwitz, and Charles Harry, Associate Research Professor
School of Public Policy

The opioid epidemic costs the U.S. over a hundred lives every day and hundreds of billions of dollars each year. The mission of Stop the Addiction Fatality Epidemic (SAFE) is to contribute in a tangible way to overcoming the addiction epidemic in the U.S. The treatment locator application helps individuals find treatment centers that match their needs quickly and independently.

Other treatment locators only identify facilities which are located the closest to the individual, not taking into account needs characteristics. SAFE identifies the facility best suited to a treatment-seeker’s specific needs as well as their proximity to the facility. The SAFE Treatment Locator draws on individual parameters from a potential patient while protecting their privacy.

SAFE completed the database integration and application programming interface. After final beta testing was completed, SAFE publicly launched the treatment locator at www.SAFEProject.us. The marketing strategy targets Maryland and, particularly, Arundel County through social media. SAFE is collecting usage data and feedback from users, which will be used to determine improvements to the application.

SAFE plans to include more information and resources related to payment (e.g., insurance information) in order to assist individuals in determining how they can pay for treatment. Additionally, future versions of the locator will include analytical data that could assist policymakers in assessing and determining growing treatment facility needs. Lastly, some cosmetic changes will be made to accommodate requests from users.

Drug Traffickers in the Maryland Circuit Court: Their Past, Their Sentences, and Prediction and Prevention of Future Violence

Jinney Smith, Ph.D., Department of Criminology and Criminal Justice
Kiminori Nakumura, Ph.D., Department of Criminology and Criminal Justice

This research examines the risk of violent recidivism, focusing on offenders of drug offenses (particularly drug trafficking) in Maryland Circuit Courts. Using three different data sources, researchers profile drug traffickers’ juvenile and criminal history and predict their risk of violent recidivism by incorporating predictors such as age at first arrest/conviction, prior violent and weapon charges, and other variables. This research also hopes to display patterns of offending and criminal history that leads to current drug offense sentences and asks whether sentences for drug traffickers are proportional to the violent recidivism risk they pose and whether or not they are effective in preventing violent recidivism.

Recent criminal justice reform efforts characterize drug offenders as non-violence offenders who warrant reduced sentences but relying on the instant offense to determine which offenders are a low public safety risk could be misleading. Though drug dealers and traffickers are targeted for punitive sanctions (i.e. mandatory minimums and sentence enhancements), little is known empirically about their future propensity for violence.

Individual sentencing data from the State Commission on Criminal Sentencing (MSCCSP), Criminal Justice Information System (CJIS), Department of Public Safety and Correctional Services (DPSCS) and the Department of Juvenile Services (DJS) are merged to identify patterns of criminal history among drug offenders and drug traffickers. To date, researchers have identified factors which may help differentiate subsets of drug offenders with a particularly heightened risk of violent recidivism, including violent crime, and are completing the data cleaning and merging. Once the final dataset is completed, the researchers will examine descriptive statistics and use a regression model to assess drug offenders and their criminal histories.

Trauma, Incarceration, and Black Men’s Health in Maryland

Kevin Roy, Ph.D., Associate Professor & Craig Fryer, Ph.D., Associate Professor
School of Public Health

This evidence-based pilot project works closely with formerly incarcerated Black men who are at-risk for continued gun and community violence, as well as drug trafficking, upon reentry back into their families and communities. The research investigates how prior experiences of trauma and violence, as well as incarceration-related trauma, shape the reentry and reintegration pathways of Black men and their families. Using a community-based participatory research (CBPR) approach, the research works closely with Black men to investigate their experiences and their strengths-based strategies to counter trauma and violence as they transition — often repeatedly — between correctional facilities and their home communities.

The researchers are conducting life history interviews with 20 Black men in both a social setting and during incarceration to identify traumatic life experiences that have led to depression, other mental and physical health issues, and incarceration and effects of definitions of masculinity on health. A focus group (8 men each) and individual life history interviews are being conducted at a correctional facility and at a barbershop in Prince George’s County. The research seeks to identify how experiences of trauma and violence (including incarceration-related trauma) shape the reentry and reintegration pathways of Black men and their families.

The focus group protocol is a more general discussion-based guide, with a discussion of what men know about trauma (with a focus on violence), how they define it, and what its effects are for men’s health. The individual interview protocol to discuss exposure to violence and traumatic events, including incarceration. Men will also discuss strategies that they have developed to cope with trauma and identify barriers that continue to affect their daily routines in employment, health, and family life.