I read that the performance of some kernel functions in SVM can change if we change the number known as kernel option. For example, this article states that kernel option of value 2 was used, http://library.binus.ac.id/eColls/eThesisdoc/Bab5/TSA-2014-0084%205.pdf.
I searched a lot about the meaning of this parameter, but every time I either found results discussing the kernel function types (polynomial, Sigmoid,etc.), or I found research papers that use this parameter without stating what it is.
So, what is 'kernel option'? And what is it called in libsvm in Weka?