Language from police body camera footage shows racial disparities in officer respect

Published on Jun 20, 2017in Proceedings of the National Academy of Sciences of the United States of America9.58
· DOI :10.1073/pnas.1702413114
Rob Voigt7
Estimated H-index: 7
(Stanford University),
Nicholas P. Camp4
Estimated H-index: 4
(Stanford University)
+ 6 AuthorsJennifer L. Eberhardt19
Estimated H-index: 19
(Stanford University)
Abstract Using footage from body-worn cameras, we analyze the respectfulness of police officer language toward white and black community members during routine traffic stops. We develop computational linguistic methods that extract levels of respect automatically from transcripts, informed by a thin-slicing study of participant ratings of officer utterances. We find that officers speak with consistently less respect toward black versus white community members, even after controlling for the race of the officer, the severity of the infraction, the location of the stop, and the outcome of the stop. Such disparities in common, everyday interactions between police and the communities they serve have important implications for procedural justice and the building of police–community trust.
Figures & Tables
  • References (30)
  • Citations (35)
#1Sharad Goel (Stanford University)H-Index: 27
#2Justin M. Rao (Microsoft)H-Index: 13
Last. Ravi ShroffH-Index: 7
view all 3 authors...
Recent studies have examined racial disparities in stop-and-frisk, a widely employed but controversial policing tactic. The statistical evidence, however, has been limited and contradictory. We investigate by analyzing three million stops in New York City over five years, focusing on cases where officers suspected the stopped individual of criminal possession of a weapon (CPW). For each CPW stop, we estimate the ex ante probability that the detained suspect has a weapon. We find that in more tha...
70 CitationsSource
#1Stephen D. Mastrofski (GMU: George Mason University)H-Index: 21
#2Tal Jonathan-ZamirH-Index: 7
Last. James J. Willis (GMU: George Mason University)H-Index: 14
view all 4 authors...
Police exercise great discretion in their dealings with the public, but most research on police discretion focuses on coercive decisions. Despite the demonstrated importance of procedural justice (PJ) for police legitimacy and overall satisfaction, the predictors of police-provided PJ in police–citizen encounters have rarely been examined. We propose a framework for assessing the choice of police officers to engage in PJ and test it using data collected in direct observations of police interacti...
32 CitationsSource
#1Tal Jonathan-ZamirH-Index: 7
Last. Shomron MoyalH-Index: 3
view all 3 authors...
Procedural justice has dominated recent discussions of police interactions with the public. It has mostly been measured from the perspective of citizens (using surveys or interviews), but several important questions about predictors and outcomes of fair police treatment are best answered using direct observations of police-citizen interactions. Building on prior observational studies, we develop and validate an instrument for measuring procedural justice as it is exercised by the police in the n...
56 CitationsSource
#1Tom R. Tyler + etalH-Index: 93
#2Robert J. BiesH-Index: 31
96 CitationsSource
#1Brian ReavesH-Index: 4
36 Citations
This is a report on President Barack Obama's executive order that created the Task Force on 21st Century Policing.
44 Citations
#1Vinodh KrishnanH-Index: 2
#2Jacob Eisenstein (Georgia Institute of Technology)H-Index: 33
We present an unsupervised model for inducing signed social networks from the content exchanged across network edges. Inference in this model solves three problems simultaneously: (1) identifying the sign of each edge; (2) characterizing the distribution over content for each edge type; (3) estimating weights for triadic features that map to theoretical models such as structural balance. We apply this model to the problem of inducing the social function of address terms, such as 'Madame', 'comra...
4 Citations
Jun 1, 2014 in ACL (Meeting of the Association for Computational Linguistics)
#1Christopher D. Manning (Stanford University)H-Index: 100
#2Mihai Surdeanu (UA: University of Arizona)H-Index: 32
Last. David McClosky (IBM)H-Index: 18
view all 6 authors...
We describe the design and use of the Stanford CoreNLP toolkit, an extensible pipeline that provides core natural language analysis. This toolkit is quite widely used, both in the research NLP community and also among commercial and government users of open source NLP technology. We suggest that this follows from a simple, approachable design, straightforward interfaces, the inclusion of robust and good quality analysis components, and not requiring use of a large amount of associated baggage.
2,917 CitationsSource
#1Viet-An Nguyen (UMD: University of Maryland, College Park)H-Index: 11
#2Jordan Boyd-Graber (UMD: University of Maryland, College Park)H-Index: 27
Last. Yuanxin Wang (RMIT: RMIT University)H-Index: 1
view all 6 authors...
Identifying influential speakers in multi-party conversations has been the focus of research in communication, sociology, and psychology for decades. It has been long acknowledged qualitatively that controlling the topic of a conversation is a sign of influence. To capture who introduces new topics in conversations, we introduce SITS--Speaker Identity for Topic Segmentation--a nonparametric hierarchical Bayesian model that is capable of discovering (1) the topics used in a set of conversations, ...
28 CitationsSource
Jun 1, 2014 in ACL (Meeting of the Association for Computational Linguistics)
#1Vinodkumar Prabhakaran (Columbia University)H-Index: 11
#2Owen Rambow (Columbia University)H-Index: 34
We introduce the problem of predicting who has power over whom in pairs of people based on a single written dialog. We propose a new set of structural features. We build a supervised learning system to predict the direction of power; our new features significantly improve the results over using previously proposed features.
12 CitationsSource
Cited By35
#1Joao Quariguasi Frota Netoa (University of Manchester)
#1J. Quariguasi Frota Neto (University of Manchester)H-Index: 11
Last. Marie Dutordoir (University of Manchester)H-Index: 12
view all 2 authors...
Abstract Remanufacturing is one of the most examined topics in the closed-loop supply chain (CLSC) literature. However, we still have limited knowledge on the characteristics of the market for remanufactured products. This study addresses this gap by using a big data analytics framework. We employ off-the-shelf, pre-trained vectors created with the Global Vectors for Word Representation (GloVe) word embedding method from a data set crawled from the Internet. The Louvain method subsequently provi...
#1Cody T. Ross (MPG: Max Planck Society)H-Index: 9
#2Bruce Winterhalder (UC Davis: University of California, Davis)H-Index: 33
Last. Richard McElreath (MPG: Max Planck Society)H-Index: 39
view all 3 authors...
Cesario et al. argue that benchmarking the relative counts of killings by police on relative crime rates, rather than relative population sizes, generates a measure of racial disparity in the use o...
#1George Wood (NU: Northwestern University)H-Index: 1
#2Tom R. Tyler + etal (Yale University)H-Index: 93
Last. Andrew V. Papachristos (NU: Northwestern University)H-Index: 24
view all 3 authors...
Existing research shows that distrust of the police is widespread and consequential for public safety. However, there is a shortage of interventions that demonstrably reduce negative police interactions with the communities they serve. A training program in Chicago attempted to encourage 8,480 officers to adopt procedural justice policing strategies. These strategies emphasize respect, neutrality, and transparency in the exercise of authority, while providing opportunities for civilians to expla...
1 CitationsSource
#1Emma Pierson (Stanford University)H-Index: 10
#2Camelia Simoiu (Stanford University)H-Index: 3
Last. Ravi Shroff (NYU: New York University)H-Index: 7
view all 11 authors...
We assessed racial disparities in policing in the United States by compiling and analysing a dataset detailing nearly 100 million traffic stops conducted across the country. We found that black drivers were less likely to be stopped after sunset, when a ‘veil of darkness’ masks one’s race, suggesting bias in stop decisions. Furthermore, by examining the rate at which stopped drivers were searched and the likelihood that searches turned up contraband, we found evidence that the bar for searching ...
2 CitationsSource
#1Cato T. LaurencinH-Index: 75
#2Joanne M. Walker (University of Connecticut Health Center)H-Index: 1
Racial profiling is a public health and health disparities issue through its disparate and adverse health impact on those targeted by this practice, as well as members of their communities. We discuss six ways police profiling and racial discrimination adversely impact Black American health. We identify four direct and two indirect ways. Four direct ways are (1) violent confrontation with police that causes injury or death; (2) police language that escalates a confrontation through micro-aggress...
2 CitationsSource
#1Sophie Trawalter (UVA: University of Virginia)H-Index: 21
#2Diane-Jo Bart-Plange (UVA: University of Virginia)
Last. Kelly M. HoffmanH-Index: 9
view all 3 authors...
Psychology has been accused of “psychologizing” racism. Here, we summarize the argument that Psychology routinely neglects structural racism and historical legacies of racism. We then discuss two cases—healthcare and police use of force—in which studying individual bias could benefit from incorporating a focus on structures and history. We close by echoing others who have advocated that Psychology move forward with a better integrated view of racism; in particular, we suggest a socioecological v...
#1Julia Mendelsohn (UM: University of Michigan)H-Index: 1
#2Yulia TsvetkovH-Index: 17
Last. Dan JurafskyH-Index: 73
view all 3 authors...
Dehumanization is a pernicious psychological process that often leads to extreme intergroup bias, hate speech, and violence aimed at targeted social groups. Despite these serious consequences and the wealth of available data, dehumanization has not yet been computationally studied on a large scale. Drawing upon social psychology research, we create a computational linguistic framework for analyzing dehumanizing language by identifying linguistic correlates of salient components of dehumanization...
#1Sharon D. Jones-Eversley (TU: Towson University)H-Index: 2
#2Johnny Rice (Coppin State University)H-Index: 1
Last. Lori James-Townes (TU: Towson University)H-Index: 1
view all 4 authors...
It is undeniably a disturbing public health crisis that requires an urgent national response to reverse and ultimately eradicate the premature deaths of young Black males. In the United States, gen...
1 CitationsSource
Computational sociology leverages new tools and data sources to expand the scope and scale of sociological inquiry. It’s opening up an exciting frontier for sociologists of every stripe—from theori...