Learning Effect Prediction Model fused with Forum Posts Classification

In order to better predict the learning effect of blended learning, provide early warning and intervention of learning, and improve the teaching quality, this paper proposes a model based on RRF(Rule and Random Forest), which can be used to classify the posts on course forum, and the classification results are calculated to obtain the score of course forum posts. Then, the SVM (Support Vector Machine) model fused with posts classification is used to predict the students' grades. After adding the scores of forum posts, the prediction accuracy increased from 85.9% to 89.03%. This learning effect prediction model was applied in blending learning, and successfully reduced the failure rate in prediction of students' final grades.