Sentiment analysis: The missing link in policing
There is great opportunity from understanding community concerns and becoming responsive to them, and great peril in ignoring those concerns
This article originally appeared in the June 2019 PoliceOne Leadership Briefing. To read the full briefing, visit Do response times matter? | The missing link in LE | Hollywood cops, and add the Leadership Briefing to your subscriptions.
This article is reprinted with permission from the National Police Foundation's OnPolicing blog.
By Chief Cameron S. McLay (Ret.)
If you ask most police officers, they will tell you their role is to respond to calls for service, fight crime and arrest violators of the law. Success is typically defined by numbers of arrests, citations and special initiatives. If crime rates are going down, and we are making a lot of contacts, citations and arrests, we must be doing a great job.
However, ask most members of the public, and they will paint a different picture.
They will tell you they want police to be responsive to concerns they have about crime and other issues that negatively impact their quality of life. They want prompt and timely police services when they have been impacted by crime, and they want the police to help them avoid becoming victims in the future. Anytime they come in contact with police, they want to be treated with dignity and respect.
Leading from the front, the NYPD has begun exploring mechanisms to incorporate sentiment analysis – data about public perceptions – as a component of its flagship performance management system. They are onto something important. The NYPD knows that it matters how members of the public feel about police services.
Using data to understand community concerns
Sentiment analysis refers to the process of gathering and analyzing the available data so that decision-makers have an informed understanding of each community’s critical issues.
The very best kind of “data” is, of course, the understanding and insights that are the byproduct of trust-based relationships with as diverse a spectrum of the public as possible.
Community surveys and feedback from community outreach efforts are the next best type of sentiment data. These methods provide insights into concerns from members of the public who may be less engaged, satisfied, or trustful of police.
By learning concerns from those less engaged, officials can carefully examine police activities to see if there are opportunities to improve outcomes and enhance trust. Knowledge about community frustrations is vital. Frustration, especially when it arises from perceived injustices and unfulfilled needs, are common precursors of unrest and disorder.
The truth is, however, that there is a level of trust involved in someone simply completing a survey. Those who distrust government, distrust police and feel alienated from the larger community, often will not participate at all.
Through the analysis of publicly available sources of data, such as social media postings, it is often possible to begin to identify those issues of greatest concern to those less engaged through other means.
How police can fulfill community needs
Sentiment analysis is about far more than measuring whether or not people like the police, it is about understanding the underlying community narratives. We seek to identify the unfulfilled needs, underlying fears and resultant frustrations most impacting how people feel about their neighborhoods, and the police officials who are paid to serve them.
By understanding those narratives, officials can earn trust by seeking to help fulfill those needs. Having gleaned insights into those issues of greatest concern, and by being responsive to those concerns, officials can demonstrate caring and responsiveness, and earn a measure of trust in the process.
As we consider the broad range of services police provide, and our role in creating safe and just communities, we should explore performance metrics to measure the broader array of services:
- Are police effective in creating public spaces where people feel safe?
- How successful are we at identifying and responding to emerging public order trends?
- Are we successfully engaging with other community stakeholders to ensure issues impacting on neighborhood quality of life problems are addressed?
Measuring outcomes of policing efforts
When attempting to measure the outcomes of policing efforts, there are three areas of concern regarding public sentiment:
- Quality of life: Community members are concerned about crime and disorder, as well as a host of other non-criminal conditions that impact their sense of safety, security and well-being in their neighborhoods and public spaces.
- Quality of service: Measuring the outcomes of police efforts also includes obtaining feedback on how people feel about the quality of the services they receive. Do members of the public believe their police to be effective? Do they feel their police are responsive to their needs?
- Perceptions of procedural justice: Do people feel the police treat them with dignity and respect, in a fair and unbiased manner, and the police are judicious in their use of coercive authority? Are they restrained in their use of force?
Police performance management systems and our use of data to direct policing efforts have created huge advances in policing as a profession. Many believe programs like CompStat, evidence-based policing and intelligence-led policing have dramatically improved our effectiveness in reducing crime. By incorporating sentiment analysis, it is possible for police officials to further measure the outcomes of our work and see if we have been successful from the perspective of those we serve.
About the author
Chief Cameron S. McLay (Ret.), formerly chief of police for the city of Pittsburgh (PA) Bureau of Police, is principal of TPL Public Safety Consulting and serves as senior adviser for PricewaterhouseCoopers Safe Cities Initiative, an initiative to enable police use of enhanced data analytics and monitoring of social risk and sentiment to improve their performance outcomes and to build public trust and confidence.