-------- BASELINE -------- 70.02667% of 1875 tokens lack PPs -------- SVM OUTPUT -------- Best SVM Accuracy: 89.44 Average SVM Accuracy: 88.63872 Model Predictions for the Best Model: true pred 0 1 0 1195 24 1 118 538 Observed Accuracy for the Best Model: 92.42667 Cohen's Kappa (Human-to-SVM): 0.8278266 -------- SVM (NOVEL DATA) -------- Novel Data Predictions for the Best Model: true pred 0 1 0 243 11 1 25 96 Novel Data Accuracy for the Best Model: 90.4 Novel Data Cohen's Kappa (Human-to-SVM): 0.7735127 -------- RANDOMFOREST OUTPUT -------- RandomForest Accuracy: 90.02667 RandomForest Feature Importance: MeanDecreaseGini maxd1 55.87135 meand1 112.94746 ranged2 168.06881 meand2 183.51608 maxd2 127.29776 sdd1 139.14237 -------- NAIVE BAYES OUTPUT -------- Naive Bayes Accuracy: 84.37333 Model Predictions for NaiveBayes: nbpred 0 1 0 1185 165 1 128 397 Observed Accuracy for NaiveBayes: 84.37333 Cohen's Kappa (Human-to-NaiveBayes): 0.6206039 -------- ENSEMBLE INFO -------- Best Ensemble Classifier: RandomForest Best Ensemble Accuracy: 90.02667 Best Improvement on Baseline: 20 Mean Ensemble Accuracy: 87.94667