True (false) positives (negatives), recall rate and precision Definition

True positive (true, TP) is predicted as positive samples by the model;

True negative (true negative, TN) is a negative sample predicted as negative by the model;

False Positive (false positive, FP) is predicted as positive negative samples by the model;

False Negative (false negative, FN) positive samples predicted as negative by the model;

True positive rate (true rate, TPR) or sensitivity)
TPR = TP/(TP + FN)
Number of positive sample prediction results/actual number of positive samples

True negative rate (true negative rate, tnr) or specificity)
Tnr = TN/(TN + FP)
Number of negative sample prediction results/actual number of negative samples

False positive rate (false positive rate, FPR)
FPR = FP/(FP + Tn)
Predicted positive negative sample result count/Actual negative sample count

False negative rate (false negative rate, FNR)
FNR = FN/(TP + FN)
Number of predicted positive sample results/actual number of positive samples

Recall rate and accuracy:

-Documents retrieved by the system ()

-Unrelated documents retrieved by the system (B)

-Related documents not retrieved by the system (c)

-Irrelevant documents retrieved by the system (d)

 

 

Intuitively, the more relevant documents retrieved by a good retrieval system, the better. The fewer irrelevant documents, the better.

Recall rate and accuracy are the most important parameters for measuring the performance of information retrieval systems.

Recall rate R: The number of retrieved documents is used as the numerator, and the total number of all relevant documents is used as the denominator, that is, r = A/(A + C)

Precision P:The number of retrieved documents is used as the numerator, and the total number of retrieved documents is used as the denominator. That is, P = A/(A + B ).

Retrieved	A	B
Not retrieved	C	D

Related

Unrelated