Computer Program To Automatically Generate News Stories From Tweets
- 01 March, 2012 01:55
Is a future without journalists possible? Will technology finally program inherent human traits essential in journalism such as judgment, experience and creativity into robots? Narrative Science, a Chicago based startup, is exploring this possibility. The company is developing a computer program capable of writing up news stories by gathering data from tweets. The program can generate a 191-word news piece by scouring tweets on any given subject. For instance, to generate an opinion piece on the likability of an American Presidential candidate, the program gathers data on the candidate and automatically writes up a piece.
Here is a sample generated response on how Newt Gingrich is doing on Twitter?
"NEWT GINGRICH GAINS ATTENTION WITH HOT-BUTTON TOPICS TAXES, CHARACTER ISSUES Newt Gingrich received the largest increase in Tweets about him today. Twitter activity associated with the candidate has shot up since yesterday, with most users tweeting about taxes and character issues. Newt Gingrich has been consistently popular on Twitter, as he has been the top riser on the site for the last four days. Conversely, the number of tweets about Ron Paul has dropped in the past 24 hours. Another traffic loser was Rick Santorum, who has also seen tweets about him fall off a bit..."
The piece is not exactly Pulitzer price worthy, but it’s an indication of a work in progress that may change journalism as we know it. Narrative Science specializes in robot written stories for a number of sectors. The robot stories mainly aim at generating short trend reports. In the future,robots may out humans in quite a number of functions!