Recall (sensitivity): from all the positive classes, how many we predicted correctly. Specificity: from all the negative classes, how many we predicted correctly. Precision: from all the classes we have predicted as positive, how many are actually positive. Accuracy: from all the classes (positive and negative), how many of them we have predicted correctly. 參考資料: toward data science: Understanding Confusion Matrix toward data science: Understanding AUC - ROC Curve AUC-ROC Curve in Machine Learning Clearly Explained
