Like a police scanner for multiple cities, Dataminr helps Patch detect breaking news across the U.S.
Share this story:
Anna Schier’s first job in media was at a small Chicago paper where she listened for breaking news over a police scanner — a role that required constant vigilance.
“I had one ear on the scanner at all times,” Schier says.
Now, as a national breaking news editor at Patch, she’s upgraded her monitoring with Dataminr, an AI platform that transforms a flood of public information — from social media posts to traffic cam footage — into manageable news streams.
Dataminr provides targeted alerts for developing stories, allowing Schier to have a real-time view of news across multiple cities at once and learn about breaking news faster. Unlike at her old job, she can finally take her ear off the scanner, confident she won’t miss a big story.
Three reasons to use Dataminr
- Dataminr can monitor thousands of public sources — from police scanners to social media — in a single, geographically-filtered feed.
- Newsrooms can customize alerts with geographic and topic-based filters to match coverage priorities.
- The tools are most valuable for covering unfamiliar markets or providing regional/national coverage where reporters lack local sources.
Newsroom overview
Patch Media operates a network of hyperlocal news sites covering over 1,900 communities across the U.S. The markets range from major metros like Los Angeles to tiny towns like Wheatland, Wyoming (population: 3,880). Coverage spans stories with national importance to the hyperlocal, but the reporting strategies remain consistent across markets.
While Patch operates as a fully digital platform, most editors and reporters work on the ground — attending municipal meetings, making courthouse visits and photographing local parades. Schier says coverage focuses on crime, fire, weather and community events. “Basically everything that you’d expect in an old school local newspaper,” she explains.
Patch newsrooms are often staffed with one reporter managed by regional editors, so its distributed system relies heavily on digital technology. Breaking news editors like Schier work shifts covering multiple communities simultaneously, providing backup support for field editors.
“If we have a story that’s breaking in an unstaffed area that might still be of interest to readers or someone’s on vacation or we just need a set of extra hands, that’s kind of where I come in,” Schier says.
Problem: Speed at scale
This distributed model creates unique challenges for breaking news coverage. At Patch, readers expect immediacy. Missing a breaking news story by even 30 minutes can mean losing audience to competitors.
“When a story breaks, get one sentence up… and then build it out from there,” Schier says of Patch’s strategy for stories that are pressing, timely and of public interest. “The most important thing is to let people know as quickly as possible.”
When Schier provides backup coverage for unfamiliar markets, there are additional hurdles to getting stories up quickly.
While local field editors rely on established networks — the vigilant parent texting from a school board meeting, the regular source at city hall, the Facebook groups where residents share updates — breaking news editors monitoring multiple territories depend mostly on digital methods to catch developing stories. This creates a critical need for Schier and her colleagues: a reliable way to detect breaking news in communities they’ve never set foot in.
Solution: AI-powered early warning
Dataminr functions as an early warning system by aggregating information from multiple sources. According to Mike D’Orio, chief product officer at Dataminr, data is collected from police scanners, traffic cameras, social media posts, government advisories, corporate disclosures, blogs and alternative social media services, and even public sensors like power outage information and flight data. The platform’s AI processes this fire hose of information and delivers geographically filtered alerts to newsroom staff.
Patch customizes their Dataminr feed by using geographic filtering and alert level settings. The platform offers three primary alert types:
- Flash for major national stories (presidential announcements, major disasters);
- Urgent for regional breaking news (crimes, accidents, weather events);
- Alert for lower-priority items.
Most Patch editors rely primarily on Urgent alerts, which capture the breadth of local breaking news without overwhelming reporters.
The system integrates into existing newsroom workflows through multiple channels. Schier receives alerts both through her email inbox and Dataminr’s web dashboard. The email integration offers better searchability for following up on previous alerts, while the dashboard provides real-time monitoring during active news shifts.
Dataminr aggregates and flags existing information from public sources. This could create accuracy challenges since the platform captures everything from official police department press releases to unverified social media posts.
“Dataminr’s job is to raise alarm bells and let me decide what to do with them,” Schier explains. “So I don’t necessarily expect that it’s going to be right and I don’t ever trust that it’s right. I always look at the source of where it’s coming from first.”
Patch treats Dataminr alerts as starting points for verification rather than publishable information. When alerts come from official sources like law enforcement agencies, editors might publish and then continue building out the story. When alerts originate from less reliable sources, verification comes first.
When alerts arrive, they include enough context for editors to make quick decisions about coverage priority. Reports of high police presence in a certain area might warrant immediate attention if it’s in a high-readership market, or it might simply trigger outreach to the local field editor for assessment. Notifications like that are preliminary and vague, but can help editors get a jump on a situation before it would otherwise be on their radar.
Dataminr can deliver alerts anywhere from five minutes to several hours before editors would discover stories without the tool — imagine combing through social media posts for tips. This head start is crucial when your audience expects your organization to be the first to break news.
Impact: Better monitoring, faster decisions
The platform’s Multi-Modal Fusion AI helps with reliability by cross-referencing information. As D’Orio, Dataminr’s chief product officer, explains: “A real breaking news event is likely to have corroboration across multiple data sources.”
The platform particularly benefits Patch’s distributed coverage model.
The tool enables Patch’s regional editors to monitor multiple markets and serve as backups for local editors when major stories break during off-hours or vacation breaks. This ensures Patch maintains real-time local news commitment across their entire network.
Beyond individual stories, Dataminr helps with strategic resource allocation. The platform’s geographic filtering allows editors to quickly assess which breaking stories warrant immediate coverage versus which can wait for local staff to return.
Verdict: The right tool for distributed coverage
While Dataminr doesn’t store journalists’ source information or reporting, newsrooms should understand that the platform monitors public information streams. The tool accelerates discovery but doesn’t replace editorial judgment.
“Nothing is going to replace the work that a local reporter has done to be informed about a community, to build relationships…. But Dataminr can be used in tandem with that to get you the story a little bit faster,” Schier says.
Initial implementation of Dataminr is relatively straightforward, but long-term success depends on proper filtering, strong newsroom workflows and staff training on verification. For newsrooms like Patch operating across multiple markets, the platform provides crucial early-warning capabilities.
Pricing is customized based on organization size, with unlimited newsroom licenses available. Newsrooms interested in specific details should contact Dataminr directly.
For newsrooms considering Dataminr, Schier’s advice applies broadly: “Use the filters, use the mapping feature. These kinds of tools work the best when you personalize them to meet your needs and to align with your goals.”
Alternatives to Dataminr
NewsWhip: Focuses on social media trending analysis rather than real-time breaking news alerts. Better suited for content optimization and audience engagement tracking than immediate news discovery.
Social News Desk: While this tool is primarily focused on being a centralized management tool for running multiple social media accounts, it is also good at combing through information on social media. In markets where audiences and local officials are active on Facebook or X (formerly known as Twitter), Social News Desk’s social listening features allow tool users to configure a dashboard that instantly updates when news happens. (If you liked the tool CrowdTangle, RIP, Social News Desk’s listening features will feel very familiar.)
Read the Help Desk’s case study on Social News Desk here.
Scanner apps and police monitors: Traditional approach offering direct access to emergency communications, but requires significant time investment and geographic limitations compared to Dataminr’s aggregated, AI-filtered approach.
Share this story:
