-------- BASELINE -------- 70.02667% of 1875 tokens lack PPs -------- SVM OUTPUT -------- Best SVM Accuracy: 93.22667 Average SVM Accuracy: 92.75815 Model Predictions for the Best Model: true pred 0 1 0 1269 8 1 44 554 Observed Accuracy for the Best Model: 97.22667 Cohen's Kappa (Human-to-SVM): 0.9351232 -------- SVM (NOVEL DATA) -------- Novel Data Predictions for the Best Model: true pred 0 1 0 258 8 1 10 99 Novel Data Accuracy for the Best Model: 95.2 Novel Data Cohen's Kappa (Human-to-SVM): 0.8829629 -------- RANDOMFOREST OUTPUT -------- RandomForest Accuracy: 94.29333 RandomForest Feature Importance: MeanDecreaseGini RAW.DCT1 137.49783 RAW.DCT2 74.16418 RAW.DCT3 345.24201 RAW.DCT4 60.58857 RAW.DCT5 116.64605 RAW.DCT6 52.84044 -------- NAIVE BAYES OUTPUT -------- Naive Bayes Accuracy: 87.78667 Model Predictions for NaiveBayes: nbpred 0 1 0 1113 29 1 200 533 Observed Accuracy for NaiveBayes: 87.78667 Cohen's Kappa (Human-to-NaiveBayes): 0.7323487 -------- ENSEMBLE INFO -------- Best Ensemble Classifier: RandomForest Best Ensemble Accuracy: 94.29333 Best Improvement on Baseline: 24.26666 Mean Ensemble Accuracy: 91.76889