-------- BASELINE -------- 70.02667% of 1875 tokens lack PPs -------- SVM OUTPUT -------- Best SVM Accuracy: 93.17333 Average SVM Accuracy: 92.58893 Model Predictions for the Best Model: true pred 0 1 0 1287 2 1 26 560 Observed Accuracy for the Best Model: 98.50667 Cohen's Kappa (Human-to-SVM): 0.9648556 -------- SVM (NOVEL DATA) -------- Novel Data Predictions for the Best Model: true pred 0 1 0 258 7 1 10 100 Novel Data Accuracy for the Best Model: 95.46667 Novel Data Cohen's Kappa (Human-to-SVM): 0.8897726 -------- RANDOMFOREST OUTPUT -------- RandomForest Accuracy: 93.49333 RandomForest Feature Importance: MeanDecreaseGini RAW.PC1 55.70341 RAW.PC2 158.65203 RAW.PC3 84.91948 RAW.PC4 25.61828 RAW.PC5 38.55981 RAW.PC6 21.44776 DIFF.PC1 263.79602 DIFF.PC2 31.93753 DIFF.PC3 32.31329 DIFF.PC4 25.71491 DIFF.PC5 17.46425 DIFF.PC6 30.58090 -------- NAIVE BAYES OUTPUT -------- Naive Bayes Accuracy: 89.54667 Model Predictions for NaiveBayes: nbpred 0 1 0 1179 62 1 134 500 Observed Accuracy for NaiveBayes: 89.54667 Cohen's Kappa (Human-to-NaiveBayes): 0.7597857 -------- ENSEMBLE INFO -------- Best Ensemble Classifier: RandomForest Best Ensemble Accuracy: 93.49333 Best Improvement on Baseline: 23.46666 Mean Ensemble Accuracy: 92.07111