Indian Journal of Science and Technology
Year: 2016, Volume: 9, Issue: 1, Pages: 1-8
Eman Salih Al-Shamery1 and Hadeel Qasem Gheni2*
*Author For Correspondence
Hadeel Qasem Gheni
Software Department, Information Technology College/ Babylon University, Iraq; [email protected]
The simplest description of a plagiarism is either a ‘copy and paste’ for a text even if the source was cited or a change in some words by taking the meaning without citing the source, where determining the meaning is the hardest and most complex task. Plagiarism can be seen as one of the cybercrime, similar to (computer viruses, computer hacking, spamming and the violation of copyrights), therefore, this subject has been interesting because it has become an important part of the ethics of scientific research. The increasing incidence of plagiarism in the higher education sector, which is considered acceptable behavior by some, since plagiarism saves time and effort, and gives better results, became a big problem faced by educational institutions. The main objective of this research is to find a suitable way to detect semantic plagiarism which occurs on the meaning and making use of synonyms and replace it instead of the original words. This research aims also to apply a pre-processing for the words of research by using tokenization and stop word removing processes, then tested whether the research enter under the specialization of computer science or not, where only such research will subject to semantic plagiarism detection by using WordNet. This research provides an effective way to detect semantic plagiarism for the written researches, especially by students who have a large plagiarism in their research.
Keywords: Plagiarism Detection, Semantic Plagiarism, Stop Words Removing, Tokenization, WordNet, WordNet Expansion
Subscribe now for latest articles and news.