First, we generate benchmarks to identify the expected values. We take the last 100 posts from a given account and of a given post type (link post, image post, etc.), and calculate the average number of interactions all those posts have at each age (15 minutes old, 60 minutes old, 5 hours old, etc.).
Then, when a new post comes in from that account, we compare it to that average and multiply the difference by the weights in each dashboard.
For details on how we do that comparison and generate the scores, learn more here.