A Narrative Method for Evaluating Documents Similarity based on Unique Strings
A precision and efficiency model of the similarity computing of texts plays an important key of duplicate documents detection. In this paper, we focus on presenting and evaluating documents similarity based on a new method viaen coding text into unique strings, called Deoxyribo Nucleic Acid (DNA) sequences. Additionally, the proposed method including an algorithm for marking as well as coloring similar paragraphs in the test document compared to other documents available in the data warehouse and developing a system for copy detection are investigated. Experimental results show that this novel approach is highly accurate for areal dataset taken from PAN. The results corroborate the advantages of the novel approach with average of 99%accuracyfor the text similarity detection with a selection threshold of ε=10-12.The results of this study are applied to implement a practical system for evaluating documents similarity at the University of Danang, Vietnam