TOOCHITECH

What signals tell X that a user wants to see more from a specific creator, and how similar are these signals to Twitter’s old follow-recommendation system? On X, following a creator is no longer the strongest signal of interest. The platform watches how users behave after seeing a post to determine whether that creator deserves repeated visibility in their feed. Understanding these signals reveals how X predicts creator affinity today—and how this system evolved from Twitter’s older, follow-centered recommendation model. 1. From explicit follows to implicit interest signals Twitter’s recommendation system treated the follow button as the primary indicator of interest. Once a user followed an account, the system assumed long-term relevance. Engagement after that point played a secondary role. X shifts away from this assumption. A follow still matters, but it is no longer enough. The platform c...

How do TikTok’s personalization models track user behavior to tailor recommendations—such as swipes, pauses, skips, and completion patterns? TikTok’s personalization models convert tiny viewer actions—swipes, pauses, skips, replays, and completion patterns—into strong signals about taste and intent. These micro-behaviors feed layered ranking systems that decide which videos to test, which audiences to target, and how aggressively to scale distribution. This article explains the signals, how they’re weighted, how the platform combines them into audience tests, and practical tactics creators can use to trigger the right behaviors. 1. Overview — personalization is a multi-layered prediction problem TikTok’s recommender is not a single rule but a stack of models that predict three things: (A) who will watch a video, (B) who will find it meaningful, and (C) who will come back for more. Micro-behaviors — swip...