@article{bibcite_66, author = {Naijia Liu* and Xinlan Hu* and Yasemin Savas* and Matthew Baum and Adam Berinsky and Allison Chaney and Christopher Lucas and Rei Mariman and Justin de Benedictis-Kessner and Andrew Guess and Dean Knox and Brandon Stewart}, title = {Short-term exposure to filter-bubble recommendation systems has limited polarization effects: Naturalistic experiments on YouTube}, abstract = {
An enormous body of literature argues that recommendation algorithms drive political polarization by creating {\textquotedblleft}filter bubbles{\textquotedblright} and {\textquotedblleft}rabbit holes.{\textquotedblright} Using four experiments with nearly 9,000 participants, we show that manipulating algorithmic recommendations to create these conditions has limited effects on opinions. Our experiments employ a custom-built video platform with a naturalistic, YouTube-like interface presenting real YouTube videos and recommendations. We experimentally manipulate YouTube{\textquoteright}s actual recommendation algorithm to simulate filter bubbles and rabbit holes by presenting ideologically balanced and slanted choices. Our design allows us to intervene in a feedback loop that has confounded the study of algorithmic polarization{\textemdash}the complex interplay between supply of recommendations and user demand for content{\textemdash}to examine downstream effects on policy attitudes. We use over 130,000 experimentally manipulated recommendations and 31,000 platform interactions to estimate how recommendation algorithms alter users{\textquoteright} media consumption decisions and, indirectly, their political attitudes. Our results cast doubt on widely circulating theories of algorithmic polarization by showing that even heavy-handed (although short-term) perturbations of real-world recommendations have limited causal effects on policy attitudes. Given our inability to detect consistent evidence for algorithmic effects, we argue the burden of proof for claims about algorithm-induced polarization has shifted. 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. Our findings reveal practical limits to effect sizes that are feasibly detectable in academic experiments.
}, year = {2025}, journal = {Proceedings of the National Academy of Sciences}, volume = {122}, publisher = {National Academy of Sciences}, issn = {0027-8424, 1091-6490}, doi = {10.1073/pnas.2318127122}, }