Query Optimization in Arabic Plagiarism Detection: An Empirical Study

Abstract

This article describes an ongoing research which intends to develop a plagiarism detection system for Arabic documents. We developed different heuristics to generate effective queries for document retrieval from the Web. The performance of those heuristics was empirically evaluated against a sizeable corpus in terms of precision, recall and fmeasure. We found that a systematic combination of different heuristics greatly improves the performance of the document retrieval system.