IDENTITY LABS / Engagement Classifier v5.2
FIG. 01
Rate vs baseline, with one post pinned open. Seventy posts plotted against their own first hour; the rail carries the live state counts and the call feed.
FIG. 02
The scoring panel open. Baseline window, sampling window and the new-audience threshold are all adjustable, and the rule they compose is stated underneath.
A post is only fast or slow relative to itself. The classifier takes each post’s own first fifteen minutes as its baseline, then scores every later reading against that line rather than against your other posts or anyone else’s. Six states come out of it, re-scored every thirty seconds for as long as the post keeps moving.
LIVE DEMO
Rate vs baseline. Each dot is one post; the dashed line is that post’s own first fifteen minutes. n = 1,284 · polled every 30s.
A live demo environment — interact with it directly.
CLASSIFIES EVERY TRACKED POST INTO
Viral · Emerging · Decaying · High reach, decaying · Flat · Unscored
