Published Paper Details:

recent years, various methods for source code classification using deep learning have been proposed. In these methods, the source code classification is performed by letting the neural network learn the source code's token sequence, etc. In that case, it is necessary to select the appropriate neural network or source code representation because the learning efficiency decreases when neural networks and source code representations that are not effective for source code classification are used for learning. However, it is not clear which neural networks or combinations of source code representations are effective for realizing high-precision source code classification methods. In this study, we compare the source code classification method using deep learning. First, we selected 3 neural networks that are widely used in existing research. Next, we compared the accuracy of a total of 6 source code classification methods in which the neural network trained the token sequence or abstract syntax tree of the source code. As a result, it was confirmed that the recursive neural network which learned the token sequence of the source code has the highest accuracy. In addition; we compared the source code classification accuracy of deep learning and non-deep learning methods, and confirmed that the classification accuracy of deep learning methods is high.