[Corpora-List] Precision and Recall

[Paul Clough]

There's also an excellent summary of evaluation measures (for IR) in this new
book:

Search Engines: Information Retrieval in Practice. Books. Croft, W. B., Metzler,
D. and Strohman, T., Pearson Education (expected 2009).  

Fortunately you can download the evaluation chapter as one of the samples here:

http://www.pearsonhighered.com/croft1epreview/samples.html


Paul.


-------------------------------------------------------
Dr. Paul Clough (Lecturer in Information Systems)

Department of Information Studies
University of Sheffield
Regent Court
Sheffield S1 4DP
Tel: +44 (0)114 2222664
Fax: +44 (0)114 2780300
Email: p.d.clough at sheffield.ac.uk
Web: http://ir.shef.ac.uk/cloughie/
-------------------------------------------------------


Quoting Adam Funk <a.funk at dcs.shef.ac.uk>:

> [18/04/08 08:39] Daniel Zeman wrote:
> > Thierry Fontenelle napsal(a):
> >> Precision: The number of correct responses divided by the total number 
> >> of actual responses.
> >>
> >> Recall: The number of correct responses divided by the total number of 
> >> possibly correct responses.
> 
> > Alternative wording I usually tell my students:
> > 
> > P = number of things I correctly found / number of things I found
> > R = number of things I correctly found / number of things I should have 
> > found
> > 
> > ("correctly found" = "I found it" AND "I should have found it")
> 
> Here's another way to look at it, which I sometimes find useful:
> 
> P = true_positives / (true_positives + false_positives)
> 
> R = true_positives / (true_positives + false_negatives)
> 
> 
> _______________________________________________
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora
> 

_______________________________________________
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora