LIS 601: Week1
Review of IR Performance Measures1

Number of
Documents
Relevant

(Rel)

Not Relevant

(Nrel)

Total
Retrieved

(Ret)

(RetRel) (RetNrel) (RetRel) + (RetNrel)

[All Docs Retrieved]
Not Retrieved

(Nret)

(NretRel) (NretNrel) (NretRel) + (NretNrel)

[All Docs. NOT Retrieved]
Total (RetRel) + (NretRel)

[All Relevant Docs]
(RetNrel) + (NretNrel)

[All NOT Relevant Docs]
(RetRel) + (RetNrel) + (NretRel) + (NretNrel)

[All Docs]

Table 1. Downie's adaptation of Pollit's2 presenation of Lancaster's3 table.


Recall:

Precision:

Fallout:

Generality:

Noise:


Notes:

1. This page adapted from: Pollit, A. S. (1989) Information storage and retrieval systems: origin, development and applications. Toronto: John Wiley & Sons, pp. 164-65.

2. Pollit, A. S. Op. cite. p.164.

3. Lancaster, F.W. (1979) Information retrieval systems: characteristics, testing and evaluation. New York: John Wiley & Sons. Quoted in Pollit, A. S. (1989)Information storage and retrieval systems: origin, development and applications. Toronto: John Wiley & Sons, p.164.