Skip to main content

Table 2 AEFN based accuracy estimates on the text evidence classification task without using ground truth.

From: Learning by aggregating experts and filtering novices: a solution to crowdsourcing problems in bioinformatics

  First Component Second Component Third Component
Annotators Estimated Sensitivity Estimated Specificity Estimated Sensitivity Estimated Specificity Estimated Sensitivity Estimated Specificity
Annotator 1 Filtered 0.7573 0.7737 Filtered
Annotator 2 0.8400 0.8445 0.8901 0.9303 0.8103 0.8798
Annotator 3 0.8984 0.9061 0.8150 0.8870 0.8235 0.8196
Annotator 4 0.7492 0.7553 Filtered 0.7184 0.8197
Annotator 5 0.8035 0.7810 0.7991 0.8199 0.8819 0.9152
  1. The estimates by five annotators for three principal components on the text evidence task are shown.