Gathering journal-level citation data from the scite API through the sciteR package, which I created for this paper, I find that journal quality varies widely across disciplines. Mathematics, physics, and chemistry have a much higher scite journal index than do medicine and economics, for example. Using a sample of 589 journals across the disciplines of math, physics, chemistry, biology, business, economics, and medicine, I attempt to use a machine-learning model to classify each journal by subject according to its scite journal index (sji).