IRS13 Evaluation Parameters chapter E. M. Keen Harvard University Gerard Salton Use, reproduction, or publication, in whole or in part, is permitted for any purpose of the United States Government. 11-56 SPECIFIC RE[OCRerr]UESTS (63 relevant) GENERAL RE[OCRerr]UESTS (135 relevant) PERFORMANCE CUT-oFF, n DOCUMENTS CUT-OFF, n DOCUMENTS ____________ =1 2 3 4 5 n= 1 2 3 4 5 OTAL RETRIEVED 21 42 63 84 105 21 42 63 84 105 RELEVANT RETRIEVED 8 17 24 25 26 11 20 27 33 38 NON-RELEV RETRIEVED 13 25 39 59 79 10 22 36 51 67 RECALL .13 .27 .38 .4o .4i .08 e15 .20 .24 .28 .00314 .0Q943 .0091 .00246 .00886 .0164 FALLOUT .00604 .01426 .00541 .01255 PRECISION .38 .4i .38 .30 .25 .52 .48 .43 .39 .36 Cran-l Collection, Abstracts, Stem dictionary, Macro Aver[OCRerr]ge over 21 Specific and 21 General Requests. Details of C[OCRerr]parison of Specific and General Requests at the First Five Document Cut-offs. Fig. 30