Cross-Language Plagiarism Detection Method: Arabic vs. English

摘要

Copying & pasting ideas across languages have created many challenges in copyrights. Though many methods have been developed to detect plagiarized content in a given language, however, detecting cross-languages plagiarism is still a challenge. This paper uses Latent Semantic Indexing (LSI) to build cross-language semantic space, from which it checks the contextual similarity of two given research papers, one in English and another in Arabic. Results shown that this method works fine in detecting cross-language English-Arabic plagiarism with 93% similarity.