In data mining, there is a multi-way trade-off between the number of features that you use, your accuracy, and the time it takes to generate a model. In theory, you'd want include every possible feature to boost accuracy; however, going about data mining in this way guarantees lengthy model generation...

In short, is J48 either a linear or a non linear classifier? I don't know. However, the decision boundaries of J48 can be made, in a way, "stepwise linear". So you can approximate a nonlinear decision boundary if you set minNumObjects low enough and set pruning to false (=...