Modeling Rabbit-Holes on YouTube

TL;DR

This paper introduces a scalable bot-based method to quantitatively analyze YouTube's rabbit-hole phenomenon, providing a formal theory and large-scale validation to understand how personalized recommendations narrow user feeds.

Contribution

It presents a novel large-scale, automated approach to detect rabbit-holes on YouTube and offers a formal theory explaining their emergence based on user interaction and video attraction.

Findings

Over 16 million recommendations analyzed

Automatic detection of rabbit-holes validated against manual labels

Theoretical model explaining the formation of rabbit-holes

Abstract

Numerous discussions have advocated the presence of a so called rabbit-hole (RH) phenomenon on social media, interested in advanced personalization to their users. This phenomenon is loosely understood as a collapse of mainstream recommendations, in favor of ultra personalized ones that lock users into narrow and specialized feeds. Yet quantitative studies are often ignoring personalization, are of limited scale, and rely on manual tagging to track this collapse. This precludes a precise understanding of the phenomenon based on reproducible observations, and thus the continuous audits of platforms. In this paper, we first tackle the scale issue by proposing a user-sided bot-centric approach that enables large scale data collection, through autoplay walks on recommendations. We then propose a simple theory that explains the appearance of these RHs. While this theory is a simplifying viewpoint on a complex and planet-wide phenomenon, it carries multiple advantages: it can be analytically modeled, and provides a general yet rigorous definition of RHs. We define them as an interplay between i) user interaction with personalization and ii) the attraction strength of certain video categories, which cause users to quickly step apart of mainstream recommendations made to fresh user profiles. We illustrate these concepts by highlighting some RHs found after collecting more than 16 million personalized recommendations on YouTube. A final validation step compares our automatically-identified RHs against manually-identified RHs from a previous research work. Together, those results pave the way for large scale and automated audits of the RH effect in recommendation systems.