We know from local publishing partners how important it is to publish content that fulfils a need for local readers. With automated texts about extreme weather, local newsrooms can service readers with fast and reliable updates, and — at the same time — allow reporters to focus on covering live developments on the ground.
United Robots provides two automated weather content products: Weather warnings and Hurricane alerts. Weather warnings are based on data from the National Weather Service and our Hurricane product is built on data from the National Hurricane Center (more on products further down).
We know from publishers who use our extreme weather products that these solve a number of problems in the local newsrooms. NJ.com (part of Advance Local) publishes automated Weather warnings, and these are the benefits they see:
Speed. The weather data is checked every five minutes, and texts are generated literally instantaneously. Says Matt Dowling, senior director of news strategy at NJ Advance Media: “The content often comes in faster than the updates from NWS on Twitter. Plus the content is already done — which means the reporter dedicated to weather can immediately link to the article.”
24/7 coverage. The automated weather warnings constitute around the clock coverage of critical community events — whether or not there are reporters in the newsroom. Dowling said: “We're unstaffed six hours on weekdays and about seven hours on weekends, and on weekends we don't always have a weather expert working. So this really helps complement the times of days where we don't have the people with the expertise to handle the larger stories on weather reporting in particular.”
Page views. During two weeks in February 2024, Advance Local published 580 weather alerts across eight of their local titles (1,100 alerts if you include updates on existing events). The content generated about half a million page views in the two weeks.
Dowling is clear that the automated content is having a positive impact in the newsroom. “This is stuff that adds value, it helps support the website, it helps support the mission and it frees up the time for our reporters to do the more meaningful work. And that has made a big difference for us.”
The NWS data covers over 100 distinct weather events and is checked every five minutes, so the automated alerts are always up-to-date. The automated weather warning content packages include state maps, with the affected county/counties highlighted in color.
There are now some 60 local newsrooms across the U.S. publishing the automated weather warnings, for example: Oregonlive and Los Angeles Daily News.
Check out what weather warnings content looks like on our showcase site.
The hurricane texts are generated from National Hurricane Center data (within 10 minutes from release) and updates typically happen every three hours, unless an urgent intermittent update is required. Data on system type, direction, speed, location, watch/warning, system name (when given), quotes from NHC and more is turned into articles, including timestamps and changes with current advisory, summary of watches, and warnings and hazards affecting land. A cone path image is sent with each text update.
We have been fine-tuning the Hurricane content for the upcoming season, including the addition of a landfall article and clearer, more natural language for the summation of the storm's events leading up to the latest update. During previous seasons, automated hurricane content was published, for example, by The Miami Herald and The Port Arthur News.
Check out what the hurricane content looks like on our showcase site.
If you are interested in more information or would like a meeting to discuss how we could help you, please get in touch with cecilia.campbell@unitedrobots.ai
