Support vector machine (SVM) is a renowned machine learning technique, which has been successfully applied to solve many practical pattern classification problems. One of the difficulties in successful implementation of SVM is its different parameters (i.e., kernel parameter(s), penalty parameter (C) and the features available in the dataset), which should be well adjusted during the training process. In this paper, a new approach called smart adaptive particle swarm optimization–support vector machine (SAPSO–SVM) is developed to adapt the parameters of optimization algorithm (i.e., inertia weight and acceleration coefficients) to the latest changes in the search space, so that each particle explicitly explores the search space based on the latest changes made to Personal best, Global best and other particle locations. In this algorithm, using the changes in Personal best and Global best at each stage of execution, the new evolution factor values are designated and the interference of the intervals of inertia weight is eradicated. Then, the states of each particle (i.e., convergence, exploitation, exploration, jumping-out) at each stage of administration, based on the interval weights, are specified accurately. By fine tuning the parameters of SAPSO, this algorithm can acquire the best optimal responses for SVM parameters. The results obtained from the SAPSO–SVM method demonstrate the superiority of this method in four different measures (i.e., sensitivity, specificity, precision, accuracy) in comparison with the other three similar ones. Finally, the top 20 features of Android botnets are somehow introduced by the proposed approach and three other approaches; firstly, these features are not encrypted by Android botnets, and secondly, are selected based on the best results.