It's a lazy journalist's dream and a dedicated journalist's nightmare. A computer program unveiled earlier this month spits out sports copy when game stats are input.
The program, called Stats Monkey was developed at Northwestern University's Intelligent Information Laboratory.
Project Stats Monkey is co-directed by Kristian Hammond and Larry Birnbaum. Both men received their Ph.Ds in Computer Science from Yale in 1986.
They demonstrated the program following the October 11 American League Division Series Game between the Los Angeles Angels and the Boston Red Sox. Below are two quotes. One is 'robocopy' and one is human copy. Read them and try to figure out which is which. (The answer is at the end of the article.)
After Chone Figgins walked, Bobby Abreu doubled and Tori Hunter was intentionally walked, the Angels were leading by one when Guerrero came to the plate against Jonathan Papelbon with two outs and the bases loaded in the ninth inning. He singled scoring Abreu from second and Figgins from third, which gave the Angels the lead for good.
The Red Sox intentionally walked Tori Hunter with runners on second and third to bring up Guerrero, a star who had long been waiting for a big October hit. Guerrero capped a three-run comeback with his go ahead hit off Papelbon, who had never before allowed a run in the postseason.
Described as "deluded killjoys" by the Toronto Star sports columnist, Cathal Kelly the team members at Northwestern have developed a complex program that uses box scores and game stats as inputs. It uses these "to figure out what the news is in the story: By analyzing changes in Win Probability and Game Scores, the system can pick out the key plays and players from any baseball game."
At the same time it is programmed with a library of narrative arcs--come from behind, weak bullpen, one bad inning. It uses these to put the main components of the statistical story "in a cohesive and compelling manner," according to the project,s website.
While baseball was used as the demonstration the team at Northwestern believes that the program could do the same thing for a variety of sports given the necessary statistics and narrative arcs.
So, which was which? The first quote is 'robocopy' and the second is man-made. More importantly, which one do you think is better written?