Animated Graphs

Normalizing and rescaling children's book ratings (2 of 2)

Note: this is the second part of a two-post series where I “fix” some of the problems with crowd-sourced ratings, like those you find for movies or books. (In this series, I look at children’s books.) In the first part, I incorporated a Bayesian prior into the rating calculation to address books with very few ratings sometimes having extreme scores (like 5 out of 5 stars) that likely don’t reflect their actual quality.

Rating children's books with empirical Bayes estimation (1 of 2)

Ratings sites – like Rotten Tomatoes and IMDb for movies or Goodreads for books – are annoying. They each seem to have their norms where the same rating means different things on different sites. A rating of 60% on one site might be good, but 6/10 (equivalent to 60%) on another site might be terrible. So you need to do some extra mental work to set your expectations based on the specific site you’re on.