We develop a random forest classifier that helps assign academic credit for a student's class forum participation. The classification target are the four classes created by student rank quartiles. Course content experts provided ground truth by ranking a limited number of post pairs. We expand this labeled set via data augmentation. We compute the relative importance of the predictors, and compare performance in matching the human expert rankings. We reach an accuracy of 0.96 for this task. To test generality and scalability, we trained the classifier on the archive of the Economics Stack Exchange reputation data. We used this classifier to predict the quartile assignments by human judges of forum posts from a university Artificial Intelligence course. Our first attempt at transfer learning reaches an average AUC of 0.66 on the augmented test set. [For the full proceedings, see ED593090.]