This paper presents a reference study of available algorithms for plagiarism
detection and it develops semantic plagiarism detection algorithm for plagiarism detection
in medical research papers by employing the Medical Ontologies available on the
World
Wide Web.
The issue of plagiarism detection in medical research written in natural languages is
a complex issue and related exact domain of medical research.
There are many used algorithms for plagiarism detection in natural language, which
are generally divided into two main categories, the first one is comparison algorithms
between files by using fingerprints of files, and files content comparison algorithms, which
include strings matching algorithms and text and tree matching algorithms.
Recently a lot of research in the field of semantic plagiarism detection algorithms
and semantic plagiarism detection algorithms were developed basing of citation analysis
models in scientific research.
In this research a system for plagiarism detection was developed using “Bing” search
engine, where tow type of ontologies used in this system, public ontology as wordNet and
many standard international ontologies in medical domain as Diseases ontology which
contains a descriptions about diseases and definitions of it and the derivation between
diseases.
