The precision <i>P</i>, recall <i>R</i> and F-measure <i>F</i> of identifying the high perceptibility users in the framework with different machine learning methods (GBM and SVM) and different parameter <i>q</i> for (a-b) MovieLens and (c-d) Netflix data sets, respectively.

<p>One can find that the recall <i>R</i> of high perceptibility user identification using GBM and SVM have little difference with the results using random forests. The precision <i>P</i> is better using GBM and SVM than using random forests.</p>