MIT Professor Creates Algorithm To Predict Trending Topics On Twitter – Before Twitter

How much do you think businesses would pay to know which topics would be trending on Twitter before they happen?

We’re not talking about paying for promoted trends here. This MIT professor claims to have figured out how to predict topics that will organically trend on Twitter before Twitter even knows they will trend. 

In case you didn’t know, a trending topic is one which people are talking about now more than at any other point, or one which has previously been popular but is now popular with a new group of people. As Twitter explains, “The Trends list captures the hottest emerging topics, not just what’s most popular. Put another way, Twitter favors novelty over popularity.”

But it seems an associate professor and one of his students know trending topics even better than Twitter – and they’ll be presenting this info at the Interdisciplinary Workshop on Information and Decision in Social Networks at MIT in November.

Associate Professor Devavrat Shah and his student, Stanislav Nikolov, will present a new algorithm that can, with 95 percent accuracy, predict which topics will trend an average of an hour and a half before Twitter’s algorithm puts them on the list — and sometimes as much as four or five hours before.

Twitter should be happy about this development as well. This would allow them to “charge a premium for ads linked to popular topics.”

How does it work? Well, it needs to be trained by combing 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.

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. . . .“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.

“The problem with this is, I don’t know that things that trend have a step function,” Shah explains. “There are a thousand things that could happen.” So instead, he says, he and Nikolov “just let the data decide.”

How very SciFi sounding, hmm? You can read more of the specifics behind this valuable development here and read the event details here!

Would knowing Twitter trends before they happen be of interest to you?

(Crystal ball with money image from Shutterstock)