Greg Lanzalotto (UPenn)

Title

Estimating Unreported and Unobservable Uses of Force Using Police Body-Worn Camera Data

Abstract

Analyses of police behavior have relied on self-reported officer accounts which may contain omissions, errors, or falsehoods. Body-worn camera (BWC) footage promised a more objective record, but resource and technological constraints leave most BWC footage unseen. In this paper, we draw on more than 700,000 BWC videos (~800 TB), and associated police administrative records from a large police department, to assess the accuracy and completeness of traditional use-of-force reports. Using an original computational classifier in concert with human annotators, we first estimate the prevalence of events caught on video that are not reported by officers. Reporting rates vary sharply by force type—weapon uses are well documented in traditional administrative files; most undocumented force involves tackling and/or manually restraining civilians. Using a modified "capture-recapture" statistical technique common in ecology, we then bound, for the first time, the share of force incidents which are fully hidden—events not captured in either paper or video records. Our analysis, combined with interviews and a blind review of force videos by a former police supervisor at the same agency, points to possible mechanisms for underreporting, including heterogeneous interpretations of policy and supervisors’ aversion to red tape.