Dec. 17 – The Spokane County Sheriff’s Office has recorded thousands of hours of footage captured by its deputies’ body cameras, making it nearly impossible for the agency to review every traffic stop, assistance stop or crime scene response.
That’s partly why the agency has turned to artificial intelligence to do the heavy lifting of reviewing the footage to evaluate how effective training is for district deputies.
The Spokane County Commission voted unanimously Tuesday to accept a nearly $1 million grant from the U.S. Department of Justice that will be used to analyze footage from body cameras worn by county deputies.
Over the next three years, an AI and data management system called ‘TrustStat’ will sift through recorded interactions between deputies and the public, with a focus on identifying ‘key behaviors and language related to de-escalation, use of force and other critical areas of deputies’ performance,” according to a Department of Justice news release.
Spokane County Sheriff John Nowels said the agency is likely the first in the country to apply the software specifically to an evaluation of training practices. He added that the program is part of the agency’s ongoing efforts to improve practices, build community trust and develop better deputies.
“My interest has always been human achievement,” Nowels said. “How do we create the most professional law enforcement officers we can, in every sense of the word? How do we make people who perform well perform even better?”
Nowels said he is hopeful the program will provide empirical data on which strategies and training are effective, and that the results could impact practices in law enforcement agencies across the country.
TrustStat, a software developed by Dallas-based Polis Solutions, is an analytics tool already used by a handful of law enforcement agencies across the country, including agencies in the company’s hometown of St. Petersburg, Florida; Kinston, North Carolina; and Alliance, Nebraska, as reported by ProPublica.
The software emerged from a former US Department of Defense research project, the Strategic Social Interaction Modules program, nicknamed ‘Good Stranger’, which aimed to better train soldiers for modern warfare, which requires them to rely on social skills to escalate brief situations or navigate uncertain circumstances.
The $40 million research project took place more than a decade ago at Fairchild Air Force Base with some law enforcement officers and former military members from Washington, as reported by NBC News. Polis Solutions, whose founder is a former Department of Defense employee, trained the TrustStat software on the program’s database.
Nowels said part of the reason TrustStat was selected, as the vendor, is an existing relationship with Sheriff’s Office training director Tony Anderman, who participated in the Department of Defense project.
TrustStat is fully automated: large language models analyze speech, and image processing algorithms identify physical movements and facial expressions captured on video, ProPublica reports.
The artificial intelligence will identify officers’ emotional responses in their interactions, starting with a baseline measure during training for the agency to compare with data from real interactions once that deputy is on the street, Nowels said.
TrustStat will analyze things like voice intonation, inflection or body position to determine what emotions may be present in the deputy and the individuals they interact with, Nowels said.
What the software does not do is assess whether a deputy’s use of force was appropriate, whether a person contacted by the deputies or the deputies themselves was acting within their rights, or whether there were policy or conduct violations. The language of the grant limits its use to an evaluation of training practices, Nowels said.
“I know there are a lot of people who want to say, ‘This artificial machine will catch officers behaving badly,’ or catch themselves behaving badly,” Nowels said. “Let me be very clear: That’s not what it was designed for, and that’s not what we’re going to use it for.”
Nowels said this does not mean he will not take appropriate action if violations are discovered during the analysis.
The tasks of determining what the entire organization hopes to answer about its training practices, reviewing the findings, and taking actionable steps will be entrusted to a board of Sheriff Office deputies ranging from everyday people to top command officers, which has yet to be completed. Nowels said.
Some of these questions will likely respond to use-of-force incidents, such as what common factors the events share, what emotions were present, and how the agency’s response could have been improved. The province may have empirical data in this regard in the coming years, Nowels said.
“But right now, the bottom line is: How do we assess the training models we use to ensure that the information we give to our deputies is received, embedded in their behavior, and retained once they’re on the road? street,” says Nowels.
