Microsoft Research project visualizes viral content (w/ video)

Mar 06, 2013 by Nancy Owano report

(Phys.org) —Trees, time lines, and bubbles. All in a day's work for a new research project at Microsoft called ViralSearch, a Microsoft Research project tool that follows the journeys of viral content. This week, Microsoft Research revealed its ViralSearch project which involves analysis to understand how-viewed content on Twitter happens to go viral. The project was introduced at a research show-and tell event. That event was Microsoft's annual TechFest, where researchers demonstrate the projects they have been working on.

ViralSearch was presented as a way to analyze content movements via . The fundamental question the project seeks to trace is, what makes some content go viral? Microsoft's ViralSearch has so far replaced mystique with , as it has gone through almost a billion pieces of information on news, videos, and photos occurring on Twitter in order to quantify viral content. As such, ViralSearch has the potential to make progress within a metrics-hungry field, as data researchers look for better insights into Internet behavior.

This video is not supported by your browser at this time.

ViralSearch can navigate and explore how content spreads across social media and how some of that content ends up as viral. ViralSearch looks at story propogation and also provides a search of the influential persons that help propel content into going viral. Researcher Jake Hofman, a computational , did the project presentation. His area of research involves applying statistics and machine learning toward social data. "ViralSearch is a new means of navigating and exploring content that goes over social media," he stated.

"We've gone through hundreds of thousands of stories that were recently posted on Twitter, looked at millions of mentions of these stories, and reconstructed trees of how these things pass from one individual to the next."

He showed how a story about Jeremy Lin was re-posted in a traditional media style of popular content traveling, where a number of people following a big outlet re-post the story and it does not go much further than that. In contrast, a viral video of a band was identified.

The project has used a scoring method to distinguish something viral from something that is merely popular.

ViralSearch currently uses Twitter as a source for all its data, tracking and visualizing how content spreads. In the bigger picture, the project belongs to an emerging research field that is attractive to software industry giants, and that is computational social science, which makes use of large-scale demographic, behavioral and network data. As Microsoft pointed out, with so much information available, from buying patterns to human contacts, "we are able to measure human behavior with precision largely thought impossible just a decade ago, creating an unprecedented opportunity to address longstanding questions in the social sciences." Microsoft described computational social science as "lying at the intersection of computer science, statistics and the social sciences."

A marketer's dream and a private citizen's nightmare? Whatever the opinion, the tools involved as presented by Hofman are impressive and promise a better understanding of content that goes viral and the impact of certain people on making go viral.

Explore further: Forging a photo is easy, but how do you spot a fake?

Related Stories

Microsoft rolls out more social Bing search

Jun 01, 2012

Microsoft on Friday rolled out a revamped Bing that includes insights from Facebook and Twitter in the biggest overhaul of the search service since its launch three years ago.

Recommended for you

Forging a photo is easy, but how do you spot a fake?

21 hours ago

Faking photographs is not a new phenomenon. The Cottingley Fairies seemed convincing to some in 1917, just as the images recently broadcast on Russian television, purporting to be satellite images showin ...

Algorithm, not live committee, performs author ranking

Nov 21, 2014

Thousands of authors' works enter the public domain each year, but only a small number of them end up being widely available. So how to choose the ones taking center-stage? And how well can a machine-learning ...

Professor proposes alternative to 'Turing Test'

Nov 19, 2014

(Phys.org) —A Georgia Tech professor is offering an alternative to the celebrated "Turing Test" to determine whether a machine or computer program exhibits human-level intelligence. The Turing Test - originally ...

Image descriptions from computers show gains

Nov 18, 2014

"Man in black shirt is playing guitar." "Man in blue wetsuit is surfing on wave." "Black and white dog jumps over bar." The picture captions were not written by humans but through software capable of accurately ...

Converting data into knowledge

Nov 17, 2014

When a movie-streaming service recommends a new film you might like, sometimes that recommendation becomes a new favorite; other times, the computer's suggestion really misses the mark. Yisong Yue, assistant ...

User comments : 0

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.