I guess I didn't completely answer. If you force the classifier to rate 100% of the data, I expect ~80%.

If you set a reasonable confidence threshold, I expect mid 80s to low 90s.

In both cases, the clustered Bayesian classifier outperforms the single classifier.

My best runs using our proprietary tokenizers and much more training data (tens of thousands of tweets, reviews, and open source training data), yield results of: 87-93% accuracy while rating 50-70% of the data. I.e. If the classifier isn't "confident" then it doesn't rate the data.

I'll run a quick test to demonstrate it's absolute accuracy. Though it definitely performs more than well enough to use in production, and is relatively little effort. It especially performs well in aggregate stats (>99% accuracy)