Introducing Media Cloud: A new tool to track how news gets covered

By Joshua Benton

Today marks the launch of a big new project from our friends a couple blocks away at the Berkman Center. It’s called Media Cloud, and its aim is to allow researchers and individuals to use data to observe how stories unfold, both in the mainstream media and in the blogs.

Media Cloud is a massive data set of news — compiled from newspapers, other established news organizations, and blogs — and a set of tools for analyzing those data. Some of the kinds of questions Media Cloud could eventually help answer:

— How do specific stories evolve over time? What path do they take when they travel among blogs, newspapers, cable TV, or other sources?
— What specific story topics won’t you hear about in [News Source X], at least compared to its competitors?
— When [News Source Y] writes about Sarah Palin [or Pakistan, or school vouchers], what’s the context of their discussion? What are the words and phrases they surround that topic with?

As Berkman Fellow Ethan Zuckerman put it, it’s an attempt to move media criticism and media analysis beyond the realm of the anecdote — to gather concrete data to back or contradict our suspicions.

Here’s a concrete example true to my Louisiana roots. These are the top 10 phrases used by The New York Times, the BBC, and Fox News around the word “Katrina” in the past six months:

This is obviously a rough analysis, but notice that Fox was more likely to include Katrina in stories that also talked about Iraq and Dick Cheney — suggesting “what went wrong with the Bush presidency” stories and a primarily political view of the story. The Times gave more prominence to the geographical names of Louisiana, Mississippi, and New Orleans, suggesting more on-the-ground reporting. And the BBC talked about it within the context of Burma, China, earthquakes, and floods — indicating it saw Katrina through the lens of other natural disasters.

Are those lists of terms open to different interpretations? Of course. But the strength of Media Cloud’s analytical powers will grow over time, as more programmers and researchers use it and build on it.

I got a sneak peak at Media Cloud Tuesday from Ethan; he (along with Stephen Shultze, Hal Roberts, and David Larochelle) is one of the people behind the project. Here’s a video of our conversation; he outlines what’s available now on the site, what some researchers are hoping to do with it, and what kinds of tools for this kind of analysis will be available to the public. (And apologies again for the audio sync issues; it’s a problem that our video provider is working on.) Full transcript after the jump. Keep reading »