Aspect-level sentiment classification aims to integrating the context to predict the sentiment polarity of aspect-specific in a text, which has been quite useful and popular, e.g. opinion survey and products' recommending in ecommerce. Many recent studies exploit a Long Short-Term Memory (LSTM) networks to perform aspect-level sentiment classification, but the limitation of long-term dependencies is not solved well, so that the semantic correlations between each two words of the text are ignored. In addition, traditional classification model adopts SoftMax function based on probability statistics as classifier, but ignores the words' features in the semantic space. Support Vector Machine (SVM) can fully use the information of characteristics and it is appropriate to make classification in the high dimension space, however which just considers the maximum distance between different classes and ignores the similarities between different features of the same classes. To address these defects, we propose the two-stages novel architecture named Self Attention Networks and Adaptive SVM (SAN-ASVM) for aspect-level sentiment classification. In the first-stage, in order to overcome the long-term dependencies, Multi-Heads Self Attention (MHSA) mechanism is applied to extract the semantic relationships between each two words, furthermore 1-hop attention mechanism is designed to pay more attention on some important words related to aspect-specific. In the second-stage, ASVM is designed to substitute the SoftMax function to perform sentiment classification, which can effectively make multi-classifications in high dimensional space. Extensive experiments on SemEval2014, SemEval2016 and Twitter datasets are conducted, compared experiments prove that SAN-ASVM model can obtains better performance.