I created a Random Forest Model for text Mining project.

On Training Dataset, i got the accuracy of :Train acc: 0.7841726618705036 

Test acc: 0.5916666666666667 

My confusion Matrix looks like:

array([[ 0, 0, 0, 0, 10], [ 0, 0, 0, 0, 23], [ 0, 0, 0, 0, 15], [ 0, 0, 0, 0, 1], [ 0, 0, 0, 0, 71]], dtype=int64) 

Also, i created Stochastic Gradient Descent Classifier

Train acc: 1.0 

Test acc: 0.5833333333333334 

Confusion Matrix:

array([[ 0, 1, 0, 1, 8], [ 0, 0, 0, 0, 23], [ 0, 1, 1, 0, 13], [ 0, 0, 0, 0, 1], [ 1, 1, 0, 0, 69]], dtype=int64) 

which model performs better, why?

any evidence of overfitting, and how can we fix it?