In our new study, Examining Algorithmic Biases in YouTube’s Recommendations of Vaccine Videos, recently published in the International Journal of Medical Informatics, we ask:
- What is the prevalence of pro-, neutral- and anti-vaccine videos on YouTube?
- In the network of vaccine-related video recommendations, does the sentiment of the video (anti-vaccine or pro-vaccine) influence the likelihood of a video being recommended? In other words, are anti-vaccine videos more likely to be recommended than pro-vaccine videos?
- Do we observe a homophily effect among pro- and anti-vaccine videos? For example, do pro-vaccine videos tend to recommend more pro-vaccine videos and vice versa?
Summary Results
Based on the social network analysis of a large sample of 2122 vaccine-related videos on YouTube, we found:
- More pro-vaccine videos (64.75%) than anti-vaccine (19.98%) videos are on YouTube, with 15.27% of videos being neutral in sentiment.
- YouTube was more likely to recommend neutral and pro-vaccine videos than anti-vaccine videos.
- There is a homophily effect in which pro-vaccine videos were more likely to recommend other pro-vaccine videos than anti-vaccine ones, and vice versa.
Compared to our 2017 study, the share of recommendations for pro-vaccine videos has noticeably increased, suggesting that YouTube’s demonetization policy of harmful content and other changes to their recommender algorithm might have been effective in reducing the visibility of anti-vaccine videos in 2019. However, there are still concerns that anti-vaccine videos are less likely to lead users to pro-vaccine videos due to the homophily effect observed in the recommendation network.
The study demonstrates the influence of YouTube’s recommender systems on the types of vaccine information users discover on YouTube. We conclude with a general discussion of the importance of algorithmic transparency in how social media platforms like YouTube decide what content to feature and recommend to its users.
For more details about the study method and other information, see the full-text at https://doi.org/10.1016/j.ijmedinf.2020.104175
Abul-Fottouh, D., Song, M. Y., & Gruzd, A. (2020). Examining algorithmic biases in YouTube’s recommendations of vaccine videos. International Journal of Medical Informatics, 104175. [Open Access]
