Abstract
The role of recommendation algorithms in online user confinement is at the heart of a fast-growing literature. Recent empirical studies generally suggest that filter bubbles may principally be observed in the case of explicit recommendation (based on user-declared preferences) rather than implicit recommendation (based on user activity). We focus on YouTube which has become a major online content provider but where confinement has until now been little-studied in a systematic manner. We aim to contribute to the above literature by showing whether recommendation on YouTube exhibits phenomena typical of filter bubbles, tending to lower the diversity of consumed content. Starting from a diverse number of seed videos, we first describe the properties of the sets of suggested videos in order to design a sound exploration protocol able to capture latent recommendation graphs recursively induced by these suggestions. These graphs form the background of potential user navigations along non-personalized recommendations. From there, be it in topological, topical or temporal terms, we show that the landscape of what we call mean-field YouTube recommendations is often prone to confinement dynamics. Moreover, the most confined recommendation graphs i.e., potential bubbles, seem to be organized around sets of videos that garner the highest audience and thus plausibly viewing time.
Highlights
The effect of algorithms in the filtering of information and interactions in online platforms is currently at heart of a very active debate, especially regarding the serendipity of contact and content discovery
Perhaps, to intuitions related to the popularization of so-called “filter bubbles”, several recent studies appear to show that algorithmic suggestions do not necessarily contribute to restrict the horizon of users
Irrespective of the sampling duration, yet even more so for shorter time spans, a “plateau” of consistently highly frequently suggested videos quickly emerges, beyond which occurrence frequencies decrease steeply. The size of this plateau may be dynamically determined through a simple change-point analysis restricted to suggestions appearing at least, say, 1% of the time
Summary
The effect of algorithms in the filtering of information and interactions in online platforms is currently at heart of a very active debate, especially regarding the serendipity of contact and content discovery. A growing literature aims at empirically comparing what happens when users do rely, at least in part, on the output of some recommendation algorithm vs when they do not. Perhaps, to intuitions related to the popularization of so-called “filter bubbles”, several recent studies appear to show that algorithmic suggestions do not necessarily contribute to restrict the horizon of users. Be it in terms of interaction or information consumption, users do not seem to be proposed less diverse content in regard to what would happen in the absence of recommendation.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have