-------- BASELINE -------- 70.02667% of 1875 tokens lack PPs -------- SVM OUTPUT -------- Best SVM Accuracy: 93.38667 Average SVM Accuracy: 92.87622 Model Predictions for the Best Model: true pred 0 1 0 1270 4 1 43 558 Observed Accuracy for the Best Model: 97.49333 Cohen's Kappa (Human-to-SVM): 0.9414491 -------- SVM (NOVEL DATA) -------- Novel Data Predictions for the Best Model: true pred 0 1 0 254 8 1 14 99 Novel Data Accuracy for the Best Model: 94.13333 Novel Data Cohen's Kappa (Human-to-SVM): 0.8585342 -------- RANDOMFOREST OUTPUT -------- RandomForest Accuracy: 93.86667 RandomForest Feature Importance: MeanDecreaseGini RAW.PC1 119.03767 RAW.PC2 325.49377 RAW.PC3 150.96677 RAW.PC4 59.14335 RAW.PC5 79.94775 RAW.PC6 51.97143 -------- NAIVE BAYES OUTPUT -------- Naive Bayes Accuracy: 88.32 Model Predictions for NaiveBayes: nbpred 0 1 0 1205 111 1 108 451 Observed Accuracy for NaiveBayes: 88.32 Cohen's Kappa (Human-to-NaiveBayes): 0.7213379 -------- ENSEMBLE INFO -------- Best Ensemble Classifier: RandomForest Best Ensemble Accuracy: 93.86667 Best Improvement on Baseline: 23.84 Mean Ensemble Accuracy: 91.85778