We report a framework for spectroscopic follow-up design for optimizing supernova photometric classification. The strategy accounts for the unavoidable mismatch between spectroscopic and photometric samples, and can be used even in the beginning of a new survey – without any initial training set. The framework falls under the umbrella of active learning (AL), a class of algorithms that aims to minimize labelling costs by identifying a few, carefully chosen, objects which have high potential in improving the classifier predictions. As a proof of concept, we use the simulated data released after the Supernova Photometric Classification Challenge (SNPCC) and a random forest classifier. Our results show that, using only 12% the number of training objects in the SNPCC spectroscopic sample, this approach is able to double purity results. Moreover, in order to take into account multiple spectroscopic observations in the same night, we propose a semi-supervised batch-mode AL algorithm which selects a set of