This study fit a Naïve Bayesian classifier to the words of exam items to predict the Bloom's taxonomy level of the items. We addressed five research questions, showing that reasonably good prediction of Bloom's level was possible, but accuracy varies across levels. In our study, performance for Level 2 was poor (Level 2 items were misclassified and other items were classified as Level 2), but the performance of the model in distinguishing Level 1 from all other levels was quite good. Applying a model developed on an IT certification exam domain to a more diverse set of items showed poor performance, suggesting that models may generalize poorly. Finally, we showed what features of items the classifier was using. Examples and implications for practice are discussed.