Skip to main content

Table 3 Summary of the classifier performance by fine-tuning the parameters (i.e., ntree and mtry)

From: A revised application of cognitive presence automatic classifiers for MOOCs: a new set of indicators revealed?

Fine-tuning process

 

ntree

mtry

Accuracy (SD)

Cohen’s κ (SD)

With the SMOTE exact method

Min

500

196

0.654 (0.034)

0.414 (0.057)

Max

1100

54

0.689 (0.043)

0.465 (0.068)

Difference

  

0.035

0.051

Without the SMOTE exact method

Min

500

2

0.659 (0.018)

0.334 (0.040)

Max

1100

94

0.694 (0.035)

0.437 (0.069)

Difference

  

0.035

0.103

  1. The bold values denote the optimal ntree and mtry values in the fine-tuning processes