Publication Details

Black-box Audit of YouTube's Video Recommendation: Investigation of Misinformation Filter Bubble Dynamics

TOMLEIN Matúš, PECHER Branislav, ŠIMKO Jakub, SRBA Ivan, MÓRO Róbert, ŠTEFANCOVÁ Elena, KOMPAN Michal, HRČKOVÁ Andrea, PODROUŽEK Juraj and BIELIKOVÁ Mária. Black-box Audit of YouTube's Video Recommendation: Investigation of Misinformation Filter Bubble Dynamics. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Sister Conferences Best Papers. Vienna: International Joint Conferences on Artificial Intelligence, 2022, pp. 5349-5353. ISBN 978-1-956792-00-3. Available from: https://www.ijcai.org/proceedings/2022/749
Czech title
Audit černé skříňky doporučení YouTube pro video: Vyšetřování dynamiky bublin filtru dezinformací
Type
conference paper
Language
english
Authors
Tomlein Matúš ()
Pecher Branislav, Ing. (DCGM FIT BUT)
Šimko Jakub, doc. Ing., Ph.D. (DCGM FIT BUT)
Srba Ivan ()
Móro Róbert ()
Štefancová Elena ()
Kompan Michal, doc. Ing., Ph.D. (DCGM FIT BUT)
Hrčková Andrea ()
Podroužek Juraj ()
Bieliková Mária, prof. Ing., PhD. (DCGM FIT BUT)
URL
Keywords

Black boxes, Bubble bursting, Bubble dynamics, Extended abstracts, YouTube

Abstract

We investigated the creation and bursting dynamics of misinformation filter bubbles on YouTube using a black-box sockpuppeting audit technique. In this study, pre-programmed agents acting as YouTube users stimulated YouTube's recommender systems: they first watched a series of misinformation promoting videos (bubble creation) and then a series of misinformation debunking videos (bubble bursting). Meanwhile, agents recorded videos recommended to them by YouTube. After manually annotating these recommendations, we were able to quantify the portion of misinformative videos among them. The results confirm the creation of filter bubbles (albeit not in all situations) and show that these bubbles can be bursted by watching credible content. Drawing a direct comparison with a previous study, we do not see improvements in overall quantities of misinformation recommended.

Published
2022
Pages
5349-5353
Proceedings
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Sister Conferences Best Papers
Conference
The 31st International Joint Conference on Artificial Intelligence, Vienna, AT
ISBN
978-1-956792-00-3
Publisher
International Joint Conferences on Artificial Intelligence
Place
Vienna, AT
DOI
10.24963/ijcai.2022/749
EID Scopus
2-s2.0-85137929479
BibTeX 
@INPROCEEDINGS{FITPUB12689,
   author = "Mat\'{u}\v{s} Tomlein and Branislav Pecher and Jakub \v{S}imko and Ivan Srba and R\'{o}bert M\'{o}ro and Elena \v{S}tefancov\'{a} and Michal Kompan and Andrea Hr\v{c}kov\'{a} and Juraj Podrou\v{z}ek and M\'{a}ria Bielikov\'{a}",
   title = "Black-box Audit of YouTube's Video Recommendation: Investigation of Misinformation Filter Bubble Dynamics",
   pages = "5349--5353",
   booktitle = "Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Sister Conferences Best Papers",
   year = 2022,
   location = "Vienna, AT",
   publisher = "International Joint Conferences on Artificial Intelligence",
   ISBN = "978-1-956792-00-3",
   doi = "10.24963/ijcai.2022/749",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12689"
}
Back to top