Newsrooms across the country have been facing a daunting task when it comes to election coverage. Local newsrooms struggle especially with limited resources. But what if AI chatbots and other digital tools allowed us to automate this work for the previews and election-night results? How might we put our limited reporting and editing resources to better use by cutting out the manual labor and instead have more time to make sense of the results to inform, empower and engage our audiences? That would be a game changer. We are setting out to try it.
On election night, our reporters spent hours collecting results by hand from 13 county websites, each with its own format. Over the last few election cycles, we have been building, testing and refinining experimental approaches to automate that work so our limited staff time could go toward analysis rather than data entry. The pipeline now gathers results from every county we cover and standardizes them into a single format. Next, we are building the tools that make those numbers useful to reporters: a live spreadsheet with registered voters, ballots cast, and turnout for each race, the same three figures from the last comparable election for context, and automatic alerts when a county posts new results. We are also automating the television ticker template we currently fill in manually each cycle.
This November, we will put that work to the test and seek to improve our election night reporting with automations that aid our staff in providing timely and accurate crucial civic information to our audience, while freeing up more of their time to do the important work of reporting the stories behind the data. Stay tuned to see what we have in store for this upcoming election, and in the meantime, read about the steps we have taken over the last few election cycles to build upon our experiments and strengthen our civic coverage:
