Saturday, November 3, 2012

Indian Origin Researchers to Present An Algorithm to Predict Twitter Trends

Indian origin researcher Devavrat Shah and his student Stanislav Nikolov have developed an algorithm that will predict the twitter trends well before it goes live on Twitter. This prediction would be done well in advance, 1-2 hours and 3-4 hours in some cases. This algorithm would be presented by the professor in the interdisciplinary workshop (MIT) in November, 2012. Sources say that it can predict trends with 95% accuracy.
Twitter trends predicted
Twitter Trends Predicted 

"In the standard approach to machine learning, Shah explains, researchers would posit a “model” — a general hypothesis about the shape of the pattern whose specifics need to be inferred. 

“You’d say, ‘Series of trending things … remain small for some time and then there is a step,’” Shah said. 

“This is a very simplistic model. Now, based on the data, you try to train for when the jump happens, and how much of a jump happens. "


 Source:- ZEE NEWS

"(The algorithm) combs through data in a sample set — in this case, data about topics that previously did and did not trend — and tries to find meaningful patterns. What distinguishes it is that it’s nonparametric, meaning that it makes no assumptions about the shape of patterns," the MIT report said.

Source:- GMA Network

Also See:-

Use Twitter Cards to Tweet in More Than 2000 Ways
Get More Twitter Followers
Free Twitter Backgrounds
Big List of Twitter Tools
Twitter Marketing Strategy
Geo Targeted Ads from Twitter

Post a Comment