Weakly Supervised Learning for Analyzing Political Campaigns on Facebook

TL;DR

This paper introduces a weakly supervised method to analyze political ads on Facebook, identifying their stance, issues, demographic targeting, and temporal dynamics to improve transparency in political messaging.

Contribution

It presents a novel weakly supervised approach for classifying political ad stance and issues, and analyzing demographic targeting and temporal patterns on social media.

Findings

Successfully identified ad stance and issues with weak supervision

Revealed demographic targeting strategies in political campaigns

Analyzed temporal dynamics of political ads during election periods

Abstract

Social media platforms are currently the main channel for political messaging, allowing politicians to target specific demographics and adapt based on their reactions. However, making this communication transparent is challenging, as the messaging is tightly coupled with its intended audience and often echoed by multiple stakeholders interested in advancing specific policies. Our goal in this paper is to take a first step towards understanding these highly decentralized settings. We propose a weakly supervised approach to identify the stance and issue of political ads on Facebook and analyze how political campaigns use some kind of demographic targeting by location, gender, or age. Furthermore, we analyze the temporal dynamics of the political ads on election polls.