Recall

• • Recall is computed as the fraction of correct instances among all instances that actually belong to the relevant subset i.e (Recall = Actual True Positive rate) .

  • Recall = TP / ( TP + FN)

Recall Graph

• • JRip has the highest True positive rate followed closely  by J48 Decision Tree .

  • Naive Bayes and SVM does very poorly with very low True positive rate i.e very large positive examples misclassified as the negative class.