Title :
Web crawler utilization for resource search on Indonesian anti-plagiarism detection: Pemanfaatan web crawler untuk pencarian referensi pada deteksi anti-plagiarisme dokumen Bahasa Indonesia
Author :
Wibowo, Agung Toto ; Arifianto, Anditya ; Oktoveri, Adeva ; Barmawi, Ari Moesriami
Author_Institution :
Inf. Dept., Telkom Univ. Bandung, Bandung, Indonesia
Abstract :
Matching one document with other documents is one of anti-plagiarism tasks. Matching can be performed both intra and extra-corpal. This paper will discuss extra-corpal matching utilize the web crawlers as reference search. The role of web-crawler described in extra-corpal anti-plagiarism architecture. Matching of plagiarism indication will use Modified Histogram Intersection based on N-Gram of term. Similarity value utilizing modified normalized histogram intersection that devoted to matching extra corpal. Based on our experiment the best accuracy is given in 0.4 and 0.5 threshold value that give 94% accuracy.
Keywords :
document handling; natural language processing; pattern matching; search engines; Indonesian anti-plagiarism detection; Web crawler; document matching; extra-corpal anti-plagiarism architecture; extra-corpal matching; modified normalized histogram intersection; n-gram; reference search; resource search; similarity value; Accuracy; Crawlers; Educational institutions; Histograms; Plagiarism; Portals; Web pages; Anti-Plagiarism Architecture; Anti-plagiarism; Extra-corpal; Modified Histogram Intersection;
Conference_Titel :
Computational Intelligence and Cybernetics (CYBERNETICSCOM), 2013 IEEE International Conference on
Conference_Location :
Yogyakarta
DOI :
10.1109/CyberneticsCom.2013.6865793
