Is Trump Angrier in Liberal Media? Surface Visual Bias in Media Coverage of Presidential Candidates With Emotion Detection Technique

• In Event: News Analysis Using Computational Methods

Abstract

Emotional display of political leaders can significantly shape voters’ evaluations of them. This study retrieved 14,955 photographs from seven news websites that ranged across the ideological spectrum (Slate, the New York Times, the Huffington Post, CNN, USA Today, Fox News, TheBlaze), and identified the emotions in 2,973 and 2,764 faces that belonged to the two candidates in the 2016 U.S. presidential election, Hillary Clinton and Donald Trump, respectively. The results demonstrated that while Clinton displayed more happiness, Trump expressed more emotions like anger, sadness, disgust, and surprise in media coverage. In addition, this pattern was more salient in liberal media outlets than in conservative media outlets. This study provides a pioneering look at the emotional display of the two candidates across media outlets and demonstrates the potential of using computational tools to analyze visual data on a large scale.

Author

• Yilang Peng, Annenberg School for Communication / U of Pennsylvania