Designing Plagiarism Detection Tool for Dogri Language
摘要
This paper describes the design of a plagiarism detection tool for the Dogri language, which is a regional language spoken in the northern Indian state of Jammu and Kashmir. The design includes an analysis of the unique characteristics of the Dogri language, such as its grammar, syntax, and vocabulary, and the development of algorithms that can detect similarities between texts. The primary objective of this research is to create a software model for automatically detecting plagiarism. Plagiarism in Dogri documents is detected by our proposed methodology which separates the text into various n-grams, which it then compares against text in the repository containing Dogri corpus as well as documents available on the web. Stop word removal and stemming methods were utilized in the preprocessing stage. For calculating the similarity score, cosine similarity was applied. A 94.3% of similarity score has been achieved.