Statistics form the backbone of sports reporting – shot percentages, batting averages, quarterback ratings, and so on. StatSheet.com, a site focused on sports statistics and analysis, is working on developing an algorithm that will create original sports reporting without human input:
Now, I’m in the process of developing completely automated sports content, which will take the form of blogs. I’m not talking just a “stat of the day” or game recaps, but a lot more. I’ve identified 21 different types of sports stories that can be automated. You could say I’m trying to make the process of writing a sports blog so easy you don’t have to do anything at all. My goal for these blogs in version 1.0 is that at least 90% of the readers think the content was created by a human. One of the nice attributes of algorithmic content is that it can be improved over time. A blogger/writer’s internal script is pretty much set. They generally don’t change or improve the quality or comprehensiveness of their content over time in a significant way, but algorithms can be upgraded continuously. The “voice” of the content can be improved.
The author points out that, while not all sports news can be easily automated (thus requiring human intervention), this algorithm should go a big way toward helping develop content, and may be especially helpful for smaller markets, where local news outlets may not have the resources to devote to covering sports.