Identifying a social media trend, a team of graduate students from Princeton have created a Web app for Facebook users that automatically generates status updates, based on previous posts.
Called 'What would I say?', the app is useful for those users that like to post
Facebook status updates, but don't want to take the time out to do so, or bother putting the words together.
The 'What would I say?' Web app, which was created during the Hack Princeton 2013 hackathon event that took place over the weekend, has already caused quite a stir on the Web. Detailing the app, the developers said "it trains a Markov Bot based on mixture model of bigram and unigram probabilities derived from your past post history."
In other words, the 'What would I say?' app looks over every status update posted by the user, and after some specialised mixing and matching, creates a new one that apparently makes sense. The developers have tried to reassure privacy advocates that their app does not store any personal information, and all the work is done on the client side.
"Don't worry, we don't store any of your personal information anywhere. In fact, we don't even have a database! All computations are done client side, so only your browser ever sees your post history."
As we mentioned, the Web app was created during a hackathon, and wasn't envisioned to become a publicly available service. Speaking to the New Yorker, the team mentioned its inspiration for creating the app: "We drank a lot of coffee and Red Bull and thought of fun things we could program that we could actually complete in a day and a half."
The Web app can be found here:
www.what-would-i-say.com. Now planning to put the popularity of the service to good use, the team has now included a link to donate to a Philippines typhoon relief fund.
Have you tried out 'What would I say'? Let us know what you feel about the service's possibilities in the comments section below. Is it just a gimmick good for few days' worth of laughs, or do you envision yourself using it now and then?