-------- BASELINE -------- 70.02667% of 1875 tokens lack PPs -------- SVM OUTPUT -------- Best SVM Accuracy: 91.41333 Average SVM Accuracy: 91.04211 Model Predictions for the Best Model: true pred 0 1 0 1239 12 1 74 550 Observed Accuracy for the Best Model: 95.41333 Cohen's Kappa (Human-to-SVM): 0.8940799 -------- SVM (NOVEL DATA) -------- Novel Data Predictions for the Best Model: true pred 0 1 0 251 9 1 17 98 Novel Data Accuracy for the Best Model: 93.06667 Novel Data Cohen's Kappa (Human-to-SVM): 0.8337312 -------- RANDOMFOREST OUTPUT -------- RandomForest Accuracy: 92.74667 RandomForest Feature Importance: MeanDecreaseGini DIFF.DCT1 239.01027 DIFF.DCT2 65.17791 DIFF.DCT3 282.79309 DIFF.DCT4 54.73973 DIFF.DCT5 97.66551 DIFF.DCT6 46.86931 -------- NAIVE BAYES OUTPUT -------- Naive Bayes Accuracy: 90.50667 Model Predictions for NaiveBayes: nbpred 0 1 0 1158 23 1 155 539 Observed Accuracy for NaiveBayes: 90.50667 Cohen's Kappa (Human-to-NaiveBayes): 0.7880877 -------- ENSEMBLE INFO -------- Best Ensemble Classifier: RandomForest Best Ensemble Accuracy: 92.74667 Best Improvement on Baseline: 22.72 Mean Ensemble Accuracy: 91.55556