ICES Seminar in Experimental Economics and Game Theory
Algorithmic Recommendations and Polarization: A Naturalistic Experiment on YouTube
Friday, November 17, 2023 12:00 PM to 1:00 PM EST
Vernon Smith Hall (formerly Metropolitan Building), 5183
The ICES Seminar in Experimental Economics and Game Theory of the Fall 2023 semester will feature:
Princeton University
Algorithmic Recommendations and Polarization: A Naturalistic Experiment on YouTube
Abstract
An enormous body of work argues that opaque recommendation algorithms contribute to political polarization by promoting increasingly extreme content. We challenge this dominant view, drawing on three large-scale, multi-wave experiments with a combined 7,851 human users, consistently showing that extremizing algorithmic recommendations has limited effects on opinions. Our experiments employ a custom-built video platform with a naturalistic, YouTube-like interface that presents real videos and recommendations drawn from YouTube. We experimentally manipulate YouTube's actual recommendation algorithm to create ideologically balanced and slanted variations. Our design allows us to intervene in a cyclical feedback loop that has long confounded the study of algorithmic polarization---the complex interplay between algorithmic supply of recommendations and user demand for consumption---to examine the downstream effects of recommendation-consumption cycles on policy attitudes. We use over 125,000 experimentally manipulated recommendations and 26,000 platform interactions to estimate how recommendation algorithms alter users' media consumption decisions and, indirectly, their political attitudes. Our work builds on recent observational studies showing that algorithm-driven "rabbit holes" of recommendations may be less prevalent than previously thought. We provide new experimental evidence casting further doubt on widely circulating theories of algorithmic polarization, showing that even large (short-term) perturbations of real-world recommendation systems that substantially modify consumption patterns have limited causal effects on policy attitudes. Our methodology, which captures and modifies the output of real-world recommendation algorithms, offers a path forward for future investigations of black-box artificial intelligence systems. However, our findings also reveal practical limits to effect sizes that are feasibly detectable in academic experiments.
For more information about the Seminar Series, please visit the Seminar Schedule homepage.
