Abstract
YouTube’s “up next” feature algorithmically selects, suggests, and displays videos to watch after the one that is currently playing. This feature has been criticized for limiting users’ exposure to a range of diverse media content and information sources; meanwhile, YouTube has reported that they have implemented various technical and policy changes to address these concerns. However, there is little publicly available data to support either the existing concerns or YouTube’s claims of having addressed them. Drawing on the idea of “platform observability,” this article combines computational and qualitative methods to investigate the types of content that the algorithms underpinning YouTube’s “up next” feature amplify over time, using three keyword search terms associated with sociocultural issues where concerns have been raised about YouTube’s role: “coronavirus,” “feminism,” and “beauty.” Over six weeks, we collected the videos (and their metadata, including channel IDs) that were highly ranked in the search results for each keyword, as well as the highly ranked recommendations associated with the videos. We repeated this exercise for three steps in the recommendation chain and then examined patterns in the recommended videos (and the channels that uploaded the videos) for each query and their variation over time. We found evidence of YouTube’s stated efforts to boost “authoritative” media outlets, but at the same time, misleading and controversial content continues to be recommended. We also found that while algorithmic recommendations offer diversity in videos over time, there are clear “winners” at the channel level that are given a visibility boost in YouTube’s “up next” feature. However, these impacts are attenuated differently depending on the nature of the issue.
Highlights
YouTube is a dominant platform for news consumption, self‐education, and opinion formation via video (Burgess & Green, 2018)
We explore patterns in the recommendations made by YouTube’s suggested videos feature over time for keyword search terms con‐ nected to sociocultural issues: “coronavirus,” “feminism,” and “beauty.” By studying the algorithmic amplification of content connected to these terms we are able to provide empirical evidence for evaluating the claims made by critics and the counterclaims made by YouTube about the role of its “up ” feature in the amplifica‐ tion of problematic, authoritative, and diverse media content
In terms of diversity of view‐ points, for “coronavirus,” we focused on media frames; for “feminism,” we paid attention to whether the most recommended videos had a feminist or an anti‐feminist stance; and for “beauty,” drawing on the work of Bishop (2018), we were interested in examining how gendered and commercial logics influenced the con‐ tent recommended for this query
Summary
YouTube is a dominant platform for news consumption, self‐education, and opinion formation via video (Burgess & Green, 2018). The recommender system behind YouTube’s “up ” feature has evolved over time and comprises mul‐ tiple components including: the “related videos” algo‐ rithm (in use in various iterations for more than a decade; see Davidson et al, 2010); personalized “recommended videos” related to the user’s watch history; and videos drawn from the same channel as the currently play‐ ing video It typically prioritizes those videos that have been recently uploaded which have a high number of views and long average watch times, and it considers the popularity of a video by including viewer satisfac‐ tion measures such as likes and dislikes (Covington et al, 2016). The system relies on deep learning approaches to improve the “quality” of recommenda‐ tions and to increase user engagement (Zhao et al, 2019)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
