Nieman Foundation at Harvard
HOME
          
LATEST STORY
How journalists can avoid amplifying misinformation in their stories
ABOUT                    SUBSCRIBE
Sept. 2, 2020, 2:15 p.m.
Aggregation & Discovery
LINK: tvnews.stanford.edu  ➚   |   Posted by: Hanaa' Tameez   |   September 2, 2020

While the use of local TV for news is declining, cable news is growing: Audience and revenue for Fox News, MSNBC, and CNN are all up this year. So which stories, and people, are getting the most airtime? Thanks to the Stanford Cable TV News Analyzer, anyone can query “the amount of time people appear and the amount of time words are heard in cable TV news.”

The tool uses “deep-learning-based image and audio analysis processing techniques” to pull from more than 270,000 hours of programming and commercial segments from Fox News, CNN, and MSNBC, dating back to January 1, 2010 and updating daily. “Computer vision is used to detect faces, identify public figures, and estimate characteristics such as gender to examine news coverage patterns. To facilitate topic analysis the transcripts are time-aligned with video content, and compared across dates, times of day and programs,” Geraldine Moriba, a journalist and filmmaker and 2019 JSK journalism fellow, explained on Medium. People can use the tool answer questions like “How much coverage does Trump receive compared to Biden? How did this change when coronavirus and the George Floyd protests came into the picture?” (There’s more on the methodology, and some findings, here.)

The tool helps “increase transparency around daily editorial choices,” Moriba noted. “How long are certain people on the screen? How often are certain words mentioned? What will you find when you compare these measurements across time, channel, and programs?”

The tool was created by the Computer Graphics Lab at Stanford University in collaboration with the John S. Knight Fellowship Program, with support from the Brown Institute for Media Innovation, Intel, Google, Amazon, and the National Science Foundation. The video dataset is from the Internet Archive’s TV News Archive.

Here are some of the queries people have run so far:

Check out the Cable TV News Analyzer here.

Show tags Show comments / Leave a comment
 
Join the 50,000 who get the freshest future-of-journalism news in our daily email.
How journalists can avoid amplifying misinformation in their stories
We need new tools to ensure visual media travels in secure ways that keep us safer online. Overlays are among these tools.
How China used the media to spread its Covid narrative — and win friends around the world
China’s image plummeted in North America, but over half of 50 nations surveyed at the end of 2020 reported coverage of China had become more positive in their national media since the onset of the pandemic.
From deepfakes to TikTok filters: How do you label AI content?
How should we label AI media in ways that people understand? And how might the labels backfire?