The AI-powered products, which are available for any newsroom to leverage, demonstrate specific ways AI can be useful for local news organizations, including:
- Automated writing of public safety incidents into the content management system of Minnesota newspaper Brainerd Dispatch. (Read the case study | Access the source code)
- Publication of Spanish-language news alerts using National Weather Service data in English by the newspaper El Vocero de Puerto Rico. (Read the case study | Access the source code)
- Automated transcription of recorded videos and summarization of the transcripts to create an article’s initial framework at San Antonio, Texas, television station KSAT-TV. (Read the case study | Access the source code)
- Sorting of news tips and coverage pitches from the public and automatically populating them into the coverage planner of Allentown, Pennsylvania, television station WFMZ-TV.
- Expanding the Minutes application, which creates transcripts of city council meetings, to include keyword identification and reporter alerts, for staff at Michigan Radio’s WUOM-FM at the University of Michigan. (Read the case study)
Four of the case studies are now available, with the final case study to be published in the coming weeks at ai.ap.org. Source code for three of the five projects is available on AP’s Github.
The Local News AI initiative, funded by the John S. and James L. Knight Foundation, began in 2021 with a survey of nearly 200 news leaders in all 50 states along with Washington D.C., Puerto Rico and Guam. The findings revealed AI knowledge interests and deficits in U.S. local newsrooms that were addressed in a six-unit online course that is still online and available for free.
After receiving and evaluating nearly four dozen project pitches, independent judges selected the five projects outlined above, which had the broadest application for other newsrooms. AP worked with development teams at Northwestern University, University of Missouri, and Stanford University to build the five AI-powered solutions for the local outlets.
The Local News AI initiative was led by program manager Aimee Rinehart and product manager Ernest Kung, who now work on AI solutions for AP and its members and customers on the AP product team.
AP will host two webinars to showcase the projects and their practical applications.
The first will feature a demonstration of each project with each local newsroom’s leadership. It will be held on Oct. 12 at 12 p.m. ET. Register here.
The second webinar, which will take place Oct. 26 at 12 p.m. ET, will allow developers to speak directly with the technology teams behind each project about how to implement the tool. Register here.
Learn more about AP’s Local News AI initiative.