Abstract & Overview
The problem of plagiarism has been widely found in the various area of academic research. It became more complicated when the resources used were taken from a different language with a suspicious document. The aim of this paper is to develop a system that can be used as early warning system in plagiarism detection. The method work as follows: do some preprocessing steps, such as: removing punctuation, removing numbers, removing stopwords, removing repeated words, and doing a process called lemmatization of words. The next process is to extract its characteristic features using improved n-Gram method and the last step is to compare the content from translated document against downloaded documents. Based on experiments, the result is indicated that the method can be used as an early warning system for plagiarism detection.