Detecting plagiarism in multiple Sinhala documents

Abstract

Availability of unlimited information resources over the Internet and the advancement of the Internet search engines such as Google to locate those resources much easily have contributed to an increase of plagiarism. Though there are a number of software tools available for detecting plagiarism in multiple English documents, no such a tool is yet available for the Sinhala language. This paper presents a novel language dependent approach to detect plagiarism in multiple Sinhala documents. It uses stemming, stop word removal and synonym replacement for text preprocessing and term frequency-inverse document frequency (tf-idf) and cosine similarity for similarity comparison. A prototype software tool was developed and interlinked with an operational Sinhala WordNet to demonstrate the viability of the proposed approach. The prototype tool was validated against a sample of Sinhala assignments from secondary school students. The assignments were also examined by an expert to determine whether they had actually been plagiarized. When compared the results of the prototype tool against those of the expert judgment, we found that our proposed approach for plagiarism detection in multiple Sinhala documents performs with an accuracy of over 80%.