the-frontline

MIT Professor invents algorithm that can predict Twitter trends

01 Nov 2012

Massachusetts Institute of Technology (MIT) associate professor Devavrat Shah has announced the creation of a new algorithm that can predict Twitter trends hours in advance.

The new algorithm was created by Professor Shah and MIT graduate student Stanislav Nikolov. The MIT alums say the new algorithm can predict trends with 95 per cent accuracy. According to Shah, the algorithm can even predict trends up to five hours before Twitter announces them.

The algorithm works by comparing past data to real-time information in a new way. Traditionally, algorithms compare similar old and new data equally.

However, Shah and Nikolov's new algorithm compares older data on a curve. The algorithm assigns a higher value to previous data that follows a similar trajectory to the present data being analyzed.

In essence, the algorithm compares old and new data in real time. So the algorithm can give a probable likelihood that a subject will trend based on old data that has been weighted in comparison to the subject.

Shah and Nikolov used a sampling of 200 subjects that did trend and 200 subjects that didn't trend to test their algorithm. The team found that the algorithm offered 95 per cent accuracy with a four per cent false-positive rate.

In a press release on the discovery Shah says the new algorithm could be used by Twitter to charge marketers for ads linked with impending trends. Which means someday you could see Twitter ads for Ford cars before you even thought you wanted to tweet about autonomous driving vehicles.

Google honors Spanish engineer Leonardo Torres-Quevedo

01 Nov 2012

The Technical University of Madrid and Google will be putting on a conference to celebrate the achievements of Spanish engineer Leonardo Torres-Quevedo. The conference will feature lectures and panel discussions exhibiting the man's many accomplishments on 7 November.

Torres-Quevedo was a famed Spanish engineer who lived from 1852 to 1936. During his lifetime he was herald for a variety of inventions in the fields of computing and civil engineering.

His first major invention came in 1887 when he built the funicular at Niagara Falls. The funicular, or Whirlpool Aero Car, is a railway that allows people to be transported up steep hillsides. In the case of Niagara Falls, the funicular takes visitors across the Fall's famed Whirlpool.

To power the Niagara Falls funicular Torres-Quevedo developed an electronic way to pull the train using ropes. The man's invention worked much the same way an elevator pulls a box up a building. The Niagara Falls funicular still stands today. Nearly a century after Torres-Quevedo built it.

Even more amazing than the Funicular is Torres-Quevedo's creation of the world's first chess playing machine. "El Ajedrecista", or The Chess Playing Machine, was an algorithmically powered machine that could play a game of chess with a human.

The machine used mechanical arms to move its chess pieces and detected its opponent's moves using electrical magnets. El Ajecdrecista deputed at the 1914 Paris World Fair and was herald as a marvel of human engineering.

Torres-Quevedo won't be the only brilliant mind of science to be recognized this year. Famed scientist Nikola Tesla will reportedly be honored with a new museum sometime in the near future. The Tesla Museum was a crowd-sourced endeavor led, in part, by the creator of the web comic The Oatmeal.

About The Frontline

Insight into the latest tech news from V3.co.uk's team of reporters

IT Infrastructure Manager

Closing Date: 13/10/2014 Working within a diverse and...

IT Development Manager

This is a unique and senior opportunity to establish...

Business Analyst

Information and Library Services Location: Avery...

Front End Developer

Front End Developer (HTML, CSS, CSS Animation, jQuery...

Browse posts by date

Cal_navigation_previousNovember 2012Cal_navigation_next
MonTueWedThuFriSatSun
       
34
       
1011
       
1718
       
19232425
       
2930

Other sites we like at The Frontline