Skip to main content
Ryan Orban

Ryan Orban

Subject
2 entries

Tiktok

Bookmarks

  1. An Empirical Investigation of Personalization Factors on TikTok

    First empirical audit of TikTok's recommendation algorithm using sock-puppet methodology, testing how language, location, follows, likes, and watch duration shape content recommendations. Follow-behavior is the dominant personalization signal, and all tested factors contribute to filter bubble formation.

  2. TikTok and the Sorting Hat

    Eugene Wei's landmark essay arguing TikTok's algorithm is the product — not the content or creators — and that it functions as a 'sorting hat' that matches users to their taste tribes faster than any previous social network. Required reading for anyone thinking about content recommendation systems.

All bookmarks