Exploiting Product Related Review Features for Fake Review Detection

Algorithm 2

Bagging the three classifiers.

Training phase;

() Initialize the parameters

 (i) , the ensemble.

() for   =   do

  (i) Choose a bootstrap set from .

  (ii) Build a classifier using .

  (iii) Add the classifier to the current ensemble,

end

() return  

Classification phase;

() Run on the input .

() The class with the maximum number of votes is chosen as the label for .