Associated Press – Generating Sports Content at Blazing Speeds

Natural Language Generation for THE ASSOCIATED PRESS

Dynamic Sports Content Written at Blazing Speed

The Associated Press used NLG to automate NCAA Division I men’s basketball previews during the 2018 season allowing their journalists to focus on writing critical, qualitative articles.

For years, sports journalists were responsible for sorting through stacks of box scores and game notes to write previews and recaps for college basketball and Minor League Baseball games. Prior to the adoption of NLG for Sports, journalists only had time to write about the top teams in each league and were unable to cover unranked matchups.

To support sports journalists, AP began automating NCAA Division I men’s basketball previews and recaps during the 2018 season, using NLG for Sports and data from Stats Perform to deliver over 5,000 previews for regular-season games. The automation of data-driven stories has freed up journalists to focus on writing critical, qualitative articles.

When the Associated Press first began automating their stories, the goal was for reporters to focus less on numbers and more on nuance, delivering more value to the news organizations that rely on them every day. Now, several years into the partnership over 50,000 articles have been automated with the help of NLG for Sports.

Automation hasn’t displaced any reporters, but instead has freed up about 20 percent of the time that was spent producing earnings reports each quarter, or the equivalent of freeing up three full-time employees across the organization. As noted by Ross Miller, a journalist for The Verge, “computers are not taking journalists’ jobs – not yet, at any rate. Instead, they are freeing up writers to think more critically about the bigger picture.”