Abstract
Cable TV news reaches millions of U.S. households each day, and decisions about who appears on the news, and what stories get talked about, can profoundly influence public opinion and discourse. In this paper, we use computational techniques to analyze a data set of nearly 24/7 video, audio, and text captions from three major U.S. cable TV networks (CNN, FOX News, and MSNBC) from the last decade. Using automated machine learning tools we detect faces in 244,038 hours of video, label their presented gender, identify prominent public figures, and align text captions to audio. We use these labels to perform face screen time and caption word frequency analyses of the contents of cable TV news. For example, we find that the ratio of female-presenting to male-presenting individuals has increased from 0.41 to 0.54 over the last decade. Donald Trump and Barack Obama received the most screen time over the last decade, with Trump receiving twice the screen time of Obama. Hillary Clinton's face was on screen 11% of the time when "email" was said in 2015 and 2016. In addition to reporting the results of our own analyses, we describe the design of an interactive web-based tool that allows the general public to perform their own screen time analyses on the entire cable TV news data set.
Abstract (translated)
URL
https://arxiv.org/abs/2008.06007
