Detecting plagiarisms in elementary programming courses

This paper proposes a method to automatically detect plagiarisms, i.e. illegal copies, among a set of programs submitted by students in elementary programming courses. In such courses, programming assignments are so simple that submitted programs are very short and similar to each other. Existing plagiarism detection methods, therefore, may yield many false positive results. The proposed method solves the problem by using three types of similarity: code, comment, and inconsistence. The inconsistence similarity, a unique feature of the method, improves the precision and recall ratios, and helps to find evidences of plagiarisms. Evaluation results using real student program assignments show the effectiveness of the proposed method.