Improving source code plagiarism detection: Lessons learned

Abstract

Computing education involves practical training through programming assignments which are frequent targets for plagiarism. For that reason, software systems for source code similarity detection are used to prevent this inappropriate behavior. In this paper, different aspects of source code plagiarism in academic environment are discussed and several improvements of plagiarism detection systems were proposed. Three main improvements of such systems were proposed: parallelization of similarity detection algorithms, similarity network visualization, and analysis of results using social network analysis.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 17 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.