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.
Associated Press | Industry: Communications & Media
The Associated Press describes itself as “one of the largest and most trusted sources of independent newsgathering, supplying a steady stream of news to its members, international subscribers and commercial customers.” The winner of 51 Pulitzer Prizes, its members include about 1,400 daily US newspapers and thousands of television and radio broadcasters. In addition to content, the company is known for style. AP Style is the definitive writing standard for journalism and for many other fields.
Time Constraints
For years, journalists at the Associated Press have had little time to focus on hard- hitting, journalistic pieces, and instead spent many hours each quarter producing financial reports. During that time, AP only had the capacity to produce 300 financial reports a quarter, leaving thousands of potential company earnings reports unwritten. USA Today’s Roger Yu referred to this time of crunching data and running on tight deadlines, the “quarterly bane of the existence of many business reporters.”
Similar to the financial reporters, sports journalists were responsible for sorting through stacks of box scores and games notes to write previews and recaps for college basketball and Minor League Baseball games. Prior to the adoption of Automated Insights’ Wordsmith, journalists only had time to write about the top teams in each league, and were unable to cover unranked match-ups.
Automated stories
The Associated Press found answers in automation with the Wordsmith platform from Automated Insights. Wordsmith uses Natural Language Generation to turn data into insightful, human-sounding narrative. In the case of the financial reports, Wordsmith transforms earnings data from Zacks Investment Research into a publishable AP story in a matter of seconds. As a result, AP now produces 4,400 quarterly earnings stories, an almost 15-fold increase over its manual efforts.
To support sports journalists, AP began automating NCAA Division I men’s basketball previews during the 2018 season, using Wordsmith and data from Stats Perform to deliver over 5,000 previews for regular-season games. Also during the 2018 season, AP began utilizing automated recaps of NCAA Division I men’s basketball games generated by Wordsmith. The automation of data-driven stories has freed up journalists to focus on writing critical, qualitative articles.
We couldn’t be happier. When you look at the 170-year history of a company like the Associated Press, part of its success has been adapting and innovating in new media formats. . . We see this as part of that history.
Increased output
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 Automated Insights’ Wordsmith.
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, 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.”
In fact, a study by researchers at Stanford and the University of Washington found that Automated Insights’ technology has had a profound effect on the stock marketing. As a result of the partnership between AP and Automated Insights, hundreds of firms that received little attention from traders are now seeing significantly more trading volume and liquidity. Now that is the power of natural language generation!
In late 2015, Automated Insights unveiled a new version of its Wordsmith platform, designed to make it easy for any professional to upload their own data and automatically generate their own narratives. The AP was one of the first companies to take a look.
In a working session with Ai, AP staff members, including the automation editor, explored how the new Wordsmith platform could generate stories using federal unemployment data. While AP reports on monthly unemployment rates for many states, it isn’t able to provide that coverage for all states. AP is testing out Wordsmith to see how it may automatically generate data-rich reports for all states each month.
Barry Bedlan, an AP Deputy Director and one of the organization’s proponents of automation, was impressed by Wordsmith’s ability to account for possible data scenarios.
“Wordsmith allows you to make the if/then decisions that a reporter would make when writing a story,” he said. “By mapping out the editorial decisions in advance, it can be used to quickly cover most scenarios and then make any changes as needed. Ultimately, I can see how Wordsmith can be used for expanded coverage at an unprecedented speed and scale.”
The overall goal: for reporters to focus less on numbers and more on nuance, and for the AP to deliver more value to the news organizations that rely on them every day.
Automated draft reports and match recaps help Yahoo! engage its massive user base.
Using Wordsmith to transform raw earnings data into thousands of publishable stories.
By using Wordsmith in their centralized analytics reporting platform, Archie, Merkle is able to translate the underlying data into insights for their users.
