Public perceptions of police behavior during traffic stops: logistic regression and machine learning approaches compared
- PDF / 1,420,126 Bytes
- 26 Pages / 439.37 x 666.142 pts Page_size
- 4 Downloads / 229 Views
Public perceptions of police behavior during traffic stops: logistic regression and machine learning approaches compared Xiaochen Hu1 · Xudong Zhang2 · Nicholas Lovrich3 Received: 11 September 2019 / Accepted: 20 August 2020 © Springer Nature Singapore Pte Ltd. 2020
Abstract Prior research on citizen perceptions of police has taken a wide-angle lens approach to the topic, with only a few studies investigating public perceptions of particular types of citizen–police encounters. In the current study, we make use of archival data on police traffic stops drawn from four waves of the BJS police–public contact surveys (PPCS) conducted in 2005, 2008, 2011, and again in 2015. In addition to employing conventional logistic regression, we make use of random forest classification to analyze survey data from a machine learning perspective. We use conventional logistic regression as a tool of explanation and random forest classification as a tool of prediction. We compare the findings generated by these two distinct analytical approaches. Substantive findings are quite similar for the explanatory and forecasting approaches. Driver’s belief that a traffic stop is legitimate is a major factor in how he or she evaluates police behavior in traffic stops, and whether the police use or threaten force during traffic stops may be the second most important factor. We draw out the implications of our work for our understanding of traffic stop dynamics, for the theory of procedural justice, for the theory of negativity bias, and for the enhanced use of machine learning in criminal justice. Keywords Public perceptions of police contacts · Traffic stop · Logistic regression · Machine learning · Random forest · Procedural justice · Negativity bias theory · Criminal justice
* Xiaochen Hu [email protected] 1
Fayetteville State University, Fayetteville, NC, USA
2
Graduate Center of the City University of New York, New York, NY, USA
3
Washington State University, Pullman, WA, USA
13
Vol.:(0123456789)
Journal of Computational Social Science
Introduction The majority of studies on public attitudes toward the police make use of citizen surveys to gather systematic information on overall public perceptions [1–3]. Only a few survey-based studies have focused on public perceptions of police–citizen encounters, and most such studies investigate matters of police legitimacy and procedural justice [4–6]. As one of the most common forms of police–citizen encounters, traffic stops have been studied by many researchers [7–14]. Even so, public attitudes toward the police in the context of traffic stops have not been investigated in any great depth to date despite their ubiquity and clear importance [15]. In this study, we explore data aggregated from four waves of police–public contact surveys (PPCS) conducted by the Bureau of Justice Statistics. We seek to identify those factors which are strongly related to public perceptions of police behavior taking formation during traffic stops. In carrying out this exploration, we use a conventional l
Data Loading...
