AST-based multi-language plagiarism detection method

To detect plagiarism on programming course, the plagiarism detection method based on Abstract Syntax Tree (AST) is proposed. First, we parse source codes into the corresponding AST by syntax analyzer and a biology sequence matching algorithm is used to calculate the similarities of programs. Second, the AST features of similar parts of the programs are extracted and then space vectors of the features are obtained. Finally, we find “copy cluster” by clustering the vectors. Experimental results show that this method has a good effect on the detection of plagiarism and can also find the “copy cluster” accurately.