First Major US Study Of Body-Cam Show Police Bias Against Black People

The first major US study of body-cam footage concluded that police, at least in Oakland, California, showed more respect to white people than to black people.

The study from Stanford University researchers analyzed the transcribed text from 981 traffic stops caught on body cams by 245 Oakland Police Department officers in 2014. White people pulled over were more likely to be called “ma’am” or “sir,” and they were more likely to hear the words “please” and “thank you” from police officers. Black people, however, didn’t get as much respect, and they were more likely to be called by their first names and even “my man.”

“Indeed, we find that white community members are 57 percent more likely to hear an officer say one of the most respectful utterances in our dataset, whereas black community members are 61 percent more likely to hear an officer say one of the least respectful utterances in our dataset,” according to the study. (PDF) The results held constant no matter the race of the officer, the study said.

The researchers point out that their survey underscores that data collected from body cams can have more uses than for just police work. They say their research model can be duplicated with other police departments.

“This work demonstrates the power of body-camera footage as an important source of data, not just as evidence,” the researchers found.

The researchers cautioned that the study was conducted with only the transcripts of 183 hours of body-cam footage, not the footage itself. And privacy concerns notwithstanding, the researchers said that more could be learned from body-cam studies if they listened to the audio and watched the footage. They wrote:

‘However, studying body-camera footage presents numerous hurdles, including privacy concerns and the raw scale of the data. The computational linguistic models presented here offer a path toward addressing both these concerns, allowing for the analysis of transcribed datasets of any size, and generating reliable ratings of respect automatically.’

A review of the actual footage could also act as a teaching moment for police departments. “In addition, footage analysis could help us better understand what linguistic acts lead interactions to go well, which can inform police training and quantify its impacts over time,” they said.

‘The studies presented here open a path toward these future opportunities and represent an important area of research for the study of policing: computational, large-scale analyses of language give us a way to examine and improve police–community interaction that we have never had before.’

For the full story visit :