Machine learning reveals how personalized climate communication can both succeed and backfire

TL;DR

This paper demonstrates how machine learning can personalize climate communication, revealing that online ads can both increase and decrease climate change beliefs depending on individual characteristics like age and ethnicity.

Contribution

It reanalyzes existing data using machine learning to uncover how personalized messages have varied effects on different demographic groups.

Findings

Ads increased climate belief in some groups

Ads decreased climate belief in others

Effectiveness varies by age and ethnicity

Abstract

Different advertising messages work for different people. Machine learning can be an effective way to personalise climate communications. In this paper we use machine learning to reanalyse findings from a recent study, showing that online advertisements increased some people's belief in climate change while resulting in decreased belief in others. In particular, we show that the effect of the advertisements could change depending on people's age and ethnicity.