Making a good first impression matters, even in social media. So why not outsource your next status update to a piece of software?
"What Would I Say?," a site created by a group of graduate students at Princeton University, quickly writes up witty status updates to post.
Granted, not everything the site spits out is Facebook gold. Many times, they're gibberish. The site itself also acknowledges that it's not perfect. "We're not trying to predict the best status update," said one of the developers during a conference call today with ABC News. "Just the funny ones."
What Would I Say was developed by Vicky Yao, Ugne Klibaite, Daniel Jiang, Pawel Przytycki, Edward Young, Harvey Cheng, Max Homilius and Alex Furger.
The site uses what's called a Markov model to figure out what to write. After sifting through a Facebook user's status updates, the site picks one word and starts calculating probabilities of other words that are likely to follow. Eventually creating a sentence.
The developers also add that though Markov models may not serve much practical use here, they are definitely valuable research tools for their own fields of research. "It's used to help with natural language processing, to look at genomic sequences, and to help build telescopes," one of the developers said.
While Facebook users have to grant What Would I Say access their profiles, it doesn't store any of the information. "We don't store any of your personal information anywhere," the website's "about" section states. "In fact, we don't even have a database!"
No comments:
Post a Comment