= Recall
{disambiguate=information retrieval}
{title2=$\mathrm{TP}/(\mathrm{TP}+\mathrm{FN})$}
<Recall (information retrieval)> measures how much of the relevant material an <information retrieval> system finds. For a relevant-document <set> $R$ and returned-document <set> $S$, it is $|R\cap S|/|R|$, provided $R$ is nonempty.<Introduction to Information Retrieval by Christopher D. Manning and others>[§8.3, printed p.155, equations 8.2 and8.4]{ref}
Suppose $R=\{2,4,6\}$ and $S=\{1,2,3,4,5\}$. Two of three relevant documents were found, so <recall (information retrieval)> is $2/3$. Adding document six raises it to one, while <precision (information retrieval)> becomes $3/6$. Returning the whole collection guarantees complete coverage of the assessed relevant <set>, but can burden the user with many irrelevant results. Estimation requires relevance judgments beyond the returned documents; empty relevant <sets> need an explicit evaluation convention.
Back to article page
