Source Code Plagiarism Detection: A Machine Intelligence Approach

Taking someone else’s work and claiming it as your own is termed as plagiarism. Plagiarism is a concerning issue in every field of education. There are various tools to detect plagiarism and help maintain the necessary integrity. This paper deals with plagiarism in the specific category of C programming assignments. Various machine learning and deep learning methods are investigated in detail along with the pros and cons. Concepts such as KNN, SVM, D-Trees, RNNs, and attention based transformer networks are tested for their effectiveness in detecting plagiarism in source code. A comprehensive dataset consisting of code pairs was prepared during the course of this research. Results obtained show that Machine Learning and Deep Learning methods provide better accuracy at detecting plagiarism than the current state of the art plagiarism detectors that use a text based approach. A tool is also presented to utilize the built software to detect plagiarism in source code.