Plagiarism and Source Deception Detection Based on Syntax Analysis


In this research, the shingle algorithm with Jaccard method are employed as a new approach to detect deception in sources in addition to detect plagiarism . Source deception occurs as a result of taking a particular text from a source and relative it to another source, while plagiarism occurs in the documents as a result of taking part or all of the text belong to another research, this approach is based on Shingle algorithm with Jaccard coefficient , Shingling is an efficient way to compare the set of shingle in the files that contain text which are used as a feature to measure the syntactic similarity of the documents and it will work with Jaccard coefficient that measures similarity between sample sets . In this proposed system, text will be checked whether it contains syntax plagiarism or not and gives a percentage of similarity with other documents , As well as research sources will be checked to detect deception in source , by matching it with available sources from Turnitin report of the same research by using shingle algorithm with Jaccard coefficient. The motivations of this work is to discovery of literary thefts that occur on the researches , especially what students are doing in their researches , also discover the deception that occurs in the sources.