Plagiarism Detection through Internet using Hybrid Artificial Neural Network and Support Vectors Machine

Abstract

Currently, most of the plagiarism detections are using similarity measurement techniques. Basically, a pair of similar sentences describes the same idea. However, not all like that, there are also sentences that are similar but have opposite meanings. This is one problem that is not easily solved by use of the technique similarity. Determination of dubious value similarity threshold on similarity method is another problem. The plagiarism threshold was adjustable, but it means uncertainty. Another problem, although the rules of plagiarism can be understood together but in practice, some people have a different opinion in determining a document, whether or not classified as plagiarism. Of the three problems, a statistical approach could possibly be the most appropriate solution. Machine learning methods like k-nearest neighbors (KNN), support vector machine (SVM), artificial neural networks (ANN) is a technique that is commonly used in solving the problem based on statistical data. This method of learning process based on statistical data to be smart resembling intelligence experts. In this case, plagiarism is data that has been validated by experts. This paper offers a hybrid approach of SVM method for detecting plagiarism. The data collection method in this work using an Internet search to ensure that a document is in the detection is up-to-date. The measurement results based on accuracy, precision and recall show that the hybrid machine learning does not always result in better performance. There is no better and vice versa. Overall testing of the four hybrid combinations concluded that the hybrid ANN-SVM method is the best performance in the case of plagiarism.