FBAdtTracker: An Interactive Data Collection and Analysis Tool for Facebook Advertisements
Ujun Jeong, Kaize Ding, Huan Liu
TL;DR
The paper addresses the challenge of disinformation in Facebook ads by introducing FBAdTracker, an integrated platform that continuously collects and analyzes ads from the Facebook Ads Library API. It presents a near real-time data pipeline built around a three-component architecture (Job Manager, Advertisement Analyzer, Advertiser Analyzer) that supports interactive job registration, visualization, and cross-sectional analysis of both ads and advertisers. Key contributions include scalable data collection beyond API query limits, structured data descriptions with policy-compliant sharing, and tools for regional and demographic ad distribution analysis. The work has practical significance for researchers aiming to perform comprehensive fact-checking and detection of misinformative advertising on social platforms.
Abstract
The growing use of social media has led to drastic changes in our decision-making. Especially, Facebook offers marketing API which promotes business to target potential groups who are likely to consume their items. However, this service can be abused by malicious advertisers who attempt to deceive people by disinformation such as propaganda and divisive opinion. To counter this problem, we introduce a new application named FBAdTracker. The purpose of this application is to provide an integrated data collection and analysis system for current research on fact-checking related to Facebook advertisements. Our system is capable of monitoring up-to-date Facebook ads and analyzing ads retrieved from Facebook Ads Library.