The Topological Face of Recommendation

Merrer, Erwan Le; Trédan, Gilles

doi:10.1007/978-3-319-72150-7_72

Cited by 6 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These walks collected personalized recommendations, that were in turn automatically labeled by the tool we will introduce in the sequel. We note that each walk duration is in the order of 100 minutes, since bots 1 https://github.com/puppeteer/puppeteer -We note that recommendations (be they contextual or personalized) are only available at the time of our collection campaign using a Javascript enabled browser: the mere use of a fast yet basic static web scrapper (such as e.g., scrappy) does not allow recommendation collection, as it was the case several years ago [22]. 2 This value is way over the 30 seconds known to be the limit of YouTube to consider a real video watch and then to increment its view counter, see e.g., https://growtraffic.com/blog/2017/08/ youtube-video-counts-view.…”

Section: Data Collection Summarymentioning

confidence: 99%

Modeling rabbit-holes on YouTube

Merrer

Trédan

Yesilkanat

2023

Soc. Netw. Anal. Min.

Self Cite

View full text Add to dashboard Cite

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 planetwide 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.

show abstract

Section: Data Collection Summarymentioning

confidence: 99%

Modeling rabbit-holes on YouTube

Merrer

Trédan

Yesilkanat

2023

Soc. Netw. Anal. Min.

Self Cite

View full text Add to dashboard Cite

show abstract

The Imitation Game: Algorithm Selection by Exploiting Black-Box Recommenders

et al. 2021

Self Cite

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract