The “Haha Ratio”: Learning from Facebook’s Emoji Reactions to Predict Persuasion Effects of Political Ads

By Medium - 2020-12-20

Description

By Minali Aggarwal, Sylvan Zheng, Sol Messing, Dan Frankowski, James Barnes, & the Barometer Team at ACRONYM Do messages criticizing Donald Trump’s performance on Covid-19 reduce his support among…

Summary

  • Learning from Facebook’s Emoji Reactions to Predict Persuasion Effects of Political Ads Do messages criticizing Donald Trump’s performance on Covid-19 reduce his support among swing voters?
  • That work suggests that an ad with a greater share of “angry” and “sad” reactions might indicate our ads working as intended — decreasing Donald Trump’s approval.
  • We also took a close look at some of our worst and best ads.
  • Just as Thompson exposed the rise of Fascism in Germany in the 1930s, we hoped our model would help us identify the best journalism to convey Trump’s anti-Democratic tendencies and incompetence.

 

Topics

  1. Machine_Learning (0.2)
  2. Backend (0.2)
  3. NLP (0.19)

Similar Articles

Home

By fast - 2020-08-21

Making neural nets uncool again

K-fold Cross Validation with PyTorch

By MachineCurve - 2021-02-02

Explanations and code examples showing you how to use K-fold Cross Validation for Machine Learning model evaluation/testing with PyTorch.