This post features a working paper that the Illuminating team presented at the 2020 SBP-BRiMS Conference. We describe and compare two computational techniques that we have used to classify Facebook and Twitter posts by message type.
Prior to the election, many analysts predicted that Arizona would be a tight race and a key battleground state for both campaign’s path to victory. Donald Trump ran ads in Arizona from several different Facebook pages. Using data collected by Illuminating, trends about the demographics Trump targeted can be examined, comparing state-specific strategy to what Trump did overall.
Illuminating is a computational journalism project that empowers journalists covering US political campaigns. The Illuminating data helps journalists see patterns and changes in how candidates address communicate to voters over time. If candidates are spending millions of dollars to micro-target voters on digital media, then someone needs to improve transparency and hold them accountable, explains Dr. Jennifer Stromer-Galley, Principal Investigator of the project.