Publication Details

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

TOMLEIN, M.; PECHER, B.; ŠIMKO, J.; SRBA, I.; MÓRO, R.; ŠTEFANCOVÁ, E.; KOMPAN, M.; HRČKOVÁ, A.; PODROUŽEK, J.; BIELIKOVÁ, M. 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. p. 5349-5353. ISBN: 978-1-956792-00-3.
Czech title
Audit černé skříňky doporučení YouTube pro video: Vyšetřování dynamiky bublin filtru dezinformací
Type
conference paper
Language
English
Authors
TOMLEIN, M.
Pecher Branislav, Ing. (DCGM)
Šimko Jakub, doc. Ing., PhD. (DCGM)
SRBA, I.
MÓRO, R.
ŠTEFANCOVÁ, E.
Kompan Michal, doc. Ing., PhD. (DCGM)
HRČKOVÁ, A.
PODROUŽEK, J.
Bieliková Mária, prof. Ing., Ph.D. (DCGM)
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
ISBN
978-1-956792-00-3
Publisher
International Joint Conferences on Artificial Intelligence
Place
Vienna
DOI
EID Scopus
BibTeX
@inproceedings{BUT180393,
  author="TOMLEIN, M. and PECHER, B. and ŠIMKO, J. and SRBA, I. and MÓRO, R. and ŠTEFANCOVÁ, E. and KOMPAN, M. and HRČKOVÁ, A. and PODROUŽEK, J. and BIELIKOVÁ, M.",
  title="Black-box Audit of YouTube's Video Recommendation: Investigation of Misinformation Filter Bubble Dynamics",
  booktitle="Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Sister Conferences Best Papers",
  year="2022",
  pages="5349--5353",
  publisher="International Joint Conferences on Artificial Intelligence",
  address="Vienna",
  doi="10.24963/ijcai.2022/749",
  isbn="978-1-956792-00-3",
  url="https://www.ijcai.org/proceedings/2022/749"
}
Back to top