Weakly Supervised Learning for Analyzing Political Campaigns on Facebook
This work addresses transparency in political campaigns on social media, which is an incremental step for researchers and policymakers.
The paper tackles the problem of understanding political messaging on Facebook by proposing a weakly supervised approach to identify the stance and issue of political ads and analyze demographic targeting and temporal dynamics in relation to election polls.
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.