This paper introduces a system for detection of plagiarism in source codes written in the PHP computer language, part of the plagiarism detection tool Anton. We used the greedy string tiling algorithm together with tokenization and hash calculation. The efficiency of the system was tested on both an artificial dataset and on real data coming from a course taught at our university. Our results are compared with other similar systems and solutions, concluding that Anton can detect all examined types of plagiarism with higher accuracy than other systems.
Všianský, R., Dlabolová, D., & Foltýnek, T. (2018). Source code plagiarism detection for PHP language. European Journal of Business Science and Technology, 3(2). https://doi.org/10.11118/ejobsat.v3i2.100