Scientists at the Binghamton University have developed a predictive algorithm through analysing tweets to forecast an individual’s behaviour well in advance.

Systems scientists at the Binghamton University, Sang Won Yoon and Sarah Lam working alongside Nathan Gnanasambandam, also Binghamton alumnus and a senior researcher at the Xerox Research’s Palo Alto Research Center, worked with 500 million tweets to structure the context-based algorithm that can pick up basIC info from social media, like ‘when’, ‘where’ and ‘what next’, aggregated with the data gathered from other sources such as credit card transactions, monitored telephone calls, e-mail and GPS data, future actions can be mapped and accurate predictions occur more than 60 percent of the time.

The team believes that this algorithm has applications in systems such as traffic control, healthcare, customer support, and more. As a post on the Binghamton blog states:

Imagine getting directions during an emergency that not only get you out of harm’s way, but get you to someplace personal where you’re safe, reducing the burden on emergency shelters. Or imagine directions that prevent a traffic jam, rather than simply route you around one.

Xerox has been funding the research team since its inception and it wouldn’t be a surprise if it puts the algorithm to use in its various enterprises.

“There’s a lot of different directions you can go,” surmises Lam.

Read more here.

(Image credit: Howard Lake)

Previous post

Bringing Big Data to Non-Profits: Bayes Impact Launches New Programme in Partnership with Five Universities

Next post

The 22 Skills of a Data Scientist...