From Fasolamatt, found in a NYT blog:
Sportswriting has long played host to some of the most glorious, along with the most cliché-ridden, exercises in journalism. As anybody on a sports beat can tell you, making game stories interesting day in and day out can be a brutal challenge, but for those with lesser ambitions, it can be something that you do in your sleep.
Now some kids at the Intelligent Information Laboratory at Northwestern University are suggesting that an average game day story can be bolted together without human intervention. Crawlers, using tried and true language, bolt in language and quotes automatically and before you know it, a story is, um, written. The project, called Stats Monkey, might have some sportswriters reaching for the bottle of Tums at a time when newspapers are reluctant to send reporters on the road to cover a team. The premise, from Stats Monkey:
Imagine that you could push a button, and magically create a story about a baseball game. That’s what the Stats Monkey system does. Given information commonly available online about many games — the box score and the play-by-play — the system automatically generates the text of a story about that game that captures the overall dynamic of the game and highlights the key plays and key players. The story includes an appropriate headline and a photo of the most important player in the game.
If that sounds like a recipe for robotic, lifeless journalism, you’re probably right, but the weird thing about Stats Monkey is how not-that-terrible the stories are.
There is also an example given from an Oct. 11 game between the Angels and Red Sox. Personally, we would have liked to have seen the computer-generated report from Game 3 of the Yankees/Twins series. We'd really like to know how Stats Monkey would have described the Nick Punto baserunning adventure.